Machine Learning · Cross-listed from eess.IV
Breast Cancer Neoadjuvant Chemotherapy Treatment Response Prediction Using Aligned Longitudinal MRI and Clinical Data
Rahul Ravi, Ruizhe Li, Tarek Abdelfatah et al. (+2 more)
Aim: This study investigates treatment response prediction to neoadjuvant chemotherapy (NACT) in breast cancer patients, using longitudinal contrast-enhanced
magnetic resonance images (CE-MRI) and clinical data. The goal is to develop machine learning (ML) models to predict pathologic complete response (PCR binary classification) and 5-year relapse-free survival status (RFS binary classification). Method: The proposed framework includes tumour
segmentation, image registration, feature extraction, and predictive modelling. Using the image registration method, MRI image features can be extracted and compared from the original tumour site at different time points, therefore monitoring the intratumor changes during NACT process. Four feature extractors, including one radiomics and three deep learning-based (MedicalNet, Segformer3D, SAM-Med3D) were implemented and compared. In combination with three feature selection methods and four ML models, predictive models are built and compared. Results: The proposed image registration-based feature extraction consistently improves the predictive models. In the PCR and RFS classification tasks logistic regression model trained on radiomic features performed the best with an AUC of 0.88 and classification accuracy of 0.85 for PCR classification, and AUC of 0.78 and classification accuracy of 0.72 for RFS classification. Conclusions: It is evidenced that the image registration method has significantly improved performance in longitudinal feature learning in predicting PCR and RFS. The radiomics feature extractor is more effective than the pre-trained deep learning feature extractors, with higher performance and better interpretability.
Read the full abstract ▾
All authors Rahul Ravi, Ruizhe Li, Tarek Abdelfatah, Stephen Chan, Xin Chen
Machine Learning
Mitigating Forgetting in Low Rank Adaptation
Joanna Sliwa, Frank Schneider, Philipp Hennig et al. (+1 more)
Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), enable fast specialization of large pre-trained models to different downstream applications. However, this process often leads to catastrophic forgetting of the model's prior domain knowledge. We address this issue with LaLoRA, a weight-space regularization technique that applies a Laplace approximation to Low-Rank Adaptation. Our approach estimates the model's confidence in each parameter and constrains updates in high-
curvature directions, preserving prior knowledge while enabling efficient target-domain learning. By applying the Laplace approximation only to the LoRA weights, the method remains lightweight. We evaluate LaLoRA by fine-tuning a Llama model for mathematical
reasoning and demonstrate an improved learning-forgetting trade-off, which can be directly controlled via the method's regularization strength. We further explore different loss landscape
curvature approximations for estimating parameter confidence, analyze the effect of the data used for the Laplace approximation, and study robustness across hyperparameters.
Read the full abstract ▾
All authors Joanna Sliwa, Frank Schneider, Philipp Hennig, Jose Miguel Hernandez-Lobato
Machine Learning · Cross-listed from cond-mat.str-el
Revisiting the Broken Symmetry Phase of Solid Hydrogen: A Neural Network Variational Monte Carlo Study
Shengdu Chai, Chen Lin, Xinyang Dong et al. (+4 more)
The
crystal structure of high-pressure solid hydrogen remains a fundamental open problem. Although the research frontier has mostly shifted toward ultra-high pressure phases above 400 GPa, we show that even the broken
symmetry phase observed around 130~GPa requires revisiting due to its intricate coupling of electronic and
nuclear degrees of freedom. Here, we develop a first principle
quantum Monte Carlo framework based on a deep neural network wave function that treats both electrons and
nuclei quantum mechanically within the constant pressure ensemble. Our calculations reveal an unreported ground-state structure candidate for the broken
symmetry phase with $Cmcm$ space group
symmetry, and we test its stability up to 96 atoms. The predicted structure quantitatively matches the experimental equation of state and gives the closest x-ray diffraction peak-position match among the tested candidates. Furthermore, our group-theoretical analysis provides a
symmetry-counting compatibility check between the $Cmcm$ structure and existing Raman and infrared spectroscopic data. Crucially, static density functional theory calculation reveals the $Cmcm$ structure as a dynamically unstable saddle point on the Born-Oppenheimer potential energy surface, demonstrating that a full
quantum many-body treatment of the problem is necessary. These results shed new light on the phase diagram of high-pressure hydrogen and call for further experimental verifications.
Read the full abstract ▾
All authors Shengdu Chai, Chen Lin, Xinyang Dong, Yuqiang Li, Wanli Ouyang, Lei Wang, X.C. Xie
Machine Learning
Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
Yuri Calleo
The modeling of high-dimensional spatio-temporal processes presents a fundamental dichotomy between the probabilistic rigor of classical geostatistics and the flexible, high-capacity representations of deep learning. While Gaussian processes offer theoretical consistency and exact uncertainty quantification, their prohibitive computational scaling renders them impractical for massive sensor networks. Conversely, modern
transformer architectures excel at sequence modeling but inherently lack a
geometric inductive bias, treating spatial sensors as permutation-invariant
tokens without a native understanding of distance. In this work, we propose a spatially-informed
transformer, a hybrid architecture that injects a geostatistical inductive bias directly into the self-
attention mechanism via a learnable covariance kernel. By formally decomposing the
attention structure into a stationary physical prior and a non-stationary data-driven residual, we impose a soft topological constraint that favors spatially proximal interactions while retaining the capacity to model complex dynamics. We demonstrate the phenomenon of “Deep Variography”, where the network successfully recovers the true spatial decay parameters of the underlying process end-to-end via backpropagation. Extensive experiments on synthetic Gaussian random fields and real-world traffic
benchmarks confirm that our method outperforms state-of-the-art graph neural networks. Furthermore, rigorous statistical validation confirms that the proposed method delivers not only superior predictive accuracy but also well-calibrated probabilistic forecasts, effectively bridging the gap between physics-aware modeling and data-driven learning.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Imputation Uncertainty in Interpretable Machine Learning Methods
Pegah Golchian and Marvin N. Wright
In real data, missing values occur frequently, which affects the interpretation with interpretable machine learning (IML) methods. Recent work considers bias and shows that model explanations may differ between imputation methods, while ignoring additional imputation uncertainty and its influence on variance and confidence intervals. We therefore compare the effects of different imputation methods on the confidence interval coverage probabilities of the IML methods permutation feature importance, partial dependence plots and Shapley values. We show that single imputation leads to underestimation of variance and that, in most cases, only multiple imputation is close to nominal coverage.
Read the full abstract ▾
Machine Learning
Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents
Paul Mangold, Eloïse Berthier and Eric Moulines
We present a novel theoretical analysis of
Federated SARSA (FedSARSA) with linear function approximation and local training. We establish convergence guarantees for FedSARSA in the presence of heterogeneity, both in local transitions and rewards, providing the first sample and communication complexity bounds in this setting. At the core of our analysis is a new, exact multi-step error expansion for single-
agent SARSA, which is of independent interest. Our analysis precisely quantifies the impact of heterogeneity, demonstrating the convergence of FedSARSA with multiple local updates. Crucially, we show that FedSARSA achieves linear speed-up with respect to the number of
agents, up to higher-order terms due to Markovian sampling. Numerical experiments support our theoretical findings.
Read the full abstract ▾
Machine Learning
You Only Train Once: Differentiable Subset Selection for Omics Data
Daphné Chopard, Jorge da Silva Gonçalves, Irene Cannistraci et al. (+2 more)
Selecting compact and informative gene subsets from single-
cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post hoc feature attribution, making selection and prediction weakly coupled. In this work, we present YOTO (you only train once), an end-to-end framework that jointly identifies discrete gene subsets and performs prediction within a single differentiable architecture. In our model, the prediction task directly guides which genes are selected, while the learned subsets, in turn, shape the predictive representation. This closed feedback loop enables the model to iteratively refine both what it selects and how it predicts during training. Unlike existing approaches, YOTO enforces sparsity so that only the selected genes contribute to inference, eliminating the need to train additional downstream classifiers. Through a multi-task learning design, the model learns shared representations across related objectives, allowing partially labeled
datasets to inform one another, and discovering gene subsets that generalize across tasks without additional training steps. We evaluate YOTO on two representative single-
cell RNA-seq
datasets, showing that it consistently outperforms state-of-the-art baselines. These results demonstrate that sparse, end-to-end, multi-task gene subset selection improves predictive performance and yields compact and meaningful gene subsets, advancing biomarker discovery and single-
cell analysis.
Read the full abstract ▾
All authors Daphné Chopard, Jorge da Silva Gonçalves, Irene Cannistraci, Thomas M. Sutter, Julia E. Vogt
Machine Learning
Polyharmonic Cascade
Yuriy N. Bakhvalov
This paper presents a deep machine learning architecture, the "polyharmonic cascade" – a sequence of packages of polyharmonic splines, where each layer is rigorously derived from the theory of random functions and the principles of indifference. This makes it possible to approximate nonlinear functions of arbitrary complexity while preserving global smoothness and a probabilistic interpretation. For the polyharmonic cascade, a training method alternative to gradient descent is proposed: instead of directly optimizing the coefficients, one solves a single global linear system on each batch with respect to the function values at fixed "constellations" of nodes. This yields synchronized updates of all layers, preserves the probabilistic interpretation of individual layers and theoretical consistency with the original model, and scales well: all computations reduce to 2D
matrix operations efficiently executed on a GPU. Fast learning without overfitting on MNIST is demonstrated.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Yao Feng, Chendong Xiang, Xinyi Mao et al. (+7 more)
Robotic arm manipulation in data-scarce settings is a highly challenging task due to the complex embodiment dynamics and diverse contexts. Recent
video-based approaches have shown great promise in capturing and transferring the temporal and physical interactions by pre-training on Internet-scale
video data. However, such methods are often not optimized for the embodiment-specific closed-loop control, typically suffering from high latency and insufficient grounding. In this paper, we present Vidarc (
Video Diffusion for Action
Reasoning and Closed-loop Control), a novel autoregressive
embodied video diffusion approach augmented by a masked inverse dynamics model. By grounding
video predictions with action-relevant masks and incorporating real-time feedback through cached autoregressive generation, Vidarc achieves fast, accurate closed-loop control. Pre-trained on one million cross-embodiment episodes, Vidarc surpasses state-of-the-art baselines, achieving at least a 15% higher success rate in real-world deployment and a 91% reduction in latency. We also highlight its robust generalization and error correction capabilities across previously unseen robotic platforms.
Read the full abstract ▾
All authors Yao Feng, Chendong Xiang, Xinyi Mao, Hengkai Tan, Zuyue Zhang, Shuhe Huang, Kaiwen Zheng, Haitian Liu, Hang Su, Jun Zhu
Machine Learning · Cross-listed from quant-ph
Fraud detection in credit card transactions using Quantum-Assisted Restricted Boltzmann Machines
João Marcos Cavalcanti de Albuquerque Neto, Gustavo Castro do Amaral and Guilherme Penello Temporão
Use cases for emerging
quantum computing platforms become economically relevant as the efficiency of processing and availability of
quantum computers increase. We assess the performance of Restricted Boltzmann Machines (RBM) assisted by
quantum computing, running on real
quantum hardware and simulators, using a real
dataset containing 145 million transactions provided by Stone, a leading Brazilian fintech, for credit card fraud detection. The results suggest that the
quantum-assisted RBM method is able to achieve superior performance in most figures of merit in comparison to classical approaches, even using current noisy
quantum annealers. Our study paves the way for implementing
quantum-assisted RBMs for general fault detection in financial systems.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Generative Multi-Objective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design
Madhav R. Muthyala, Farshud Sorourifar, Tianhong Tan et al. (+2 more)
Designing molecules that must satisfy multiple, often conflicting objectives is a central challenge in molecular discovery. The enormous size of chemical space and the cost of high-fidelity simulations have driven the development of machine learning-guided strategies for accelerating design with limited data. Among these,
Bayesian optimization (BO) offers a principled framework for sample-efficient search, while generative models provide a mechanism to propose novel, diverse candidates beyond fixed libraries. However, existing methods that couple the two often rely on continuous latent spaces, which introduces both architectural
entanglement and scalability challenges. This work introduces an alternative, modular "generate-then-optimize" framework for de novo multi-objective molecular design/discovery. At each iteration, a generative model is used to construct a large, diverse pool of candidate molecules, after which a novel acquisition function, qPMHI (multi-point Probability of Maximum Hypervolume Improvement), is used to optimally select a batch of candidates most likely to induce the largest Pareto front expansion. The key insight is that qPMHI decomposes additively, enabling exact, scalable batch selection via only simple ranking of probabilities that can be easily estimated with Monte Carlo sampling. We
benchmark the framework against state-of-the-art latent-space and discrete molecular optimization methods, demonstrating significant improvements across synthetic
benchmarks and application-driven tasks. Specifically, in a case study related to sustainable energy storage, we show that our approach quickly uncovers novel, diverse, and high-performing organic (quinone-based) cathode materials for aqueous redox flow battery applications.
Read the full abstract ▾
All authors Madhav R. Muthyala, Farshud Sorourifar, Tianhong Tan, You Peng, Joel A. Paulson
Machine Learning
Learning-Based Estimation of Spatially Resolved Scatter Radiation Fields in Interventional Radiology
Felix Lehner, Pasquale Lombardo, Susana Castillo et al. (+2 more)
We present three variants of a lightweight, fully connected artificial neural network, suited for interactive estimation of three-dimensional, spatially resolved volumes of scattered radiation fields and a corresponding training pipeline for radiation protection dosimetry in medical radiation fields, such as those found in interventional radiology and cardiology. Accompanying, we present three different synthetically generated
datasets with increasing complexity for training, generated using RadField3D, a Monte Carlo simulation application based on Geant4. As the primary scatter object, we employed the torso of a male Alderson RANDO phantom. On those
datasets, we evaluate convolutional and fully connected architectures of neural networks to demonstrate which design decisions work well for reconstructing the fluence and spectra distributions over the spatial domain of such radiation fields. All our
datasets, as well as our training pipeline, are published as open source in separate repositories. To evaluate the presented neural networks, we define and assess several metrics. Across these measures, the model variants demonstrate good spatial agreement between predicted and ground-truth radiation fields, particularly within specific regions of interest within the radiation field. Of particular relevance for potential application in out-of-field dosimetry is the SMAPE of the scatter radiation field, which represents the most challenging metric and was consistently above 84 %.
Read the full abstract ▾
All authors Felix Lehner, Pasquale Lombardo, Susana Castillo, Oliver Hupe, Marcus Magnor
Machine Learning
Trust-Region Adaptive Policy Optimization
Mingyu Su, Jian Guan, Yuxian Gu et al. (+2 more)
Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large
language models' (LLMs) complex
reasoning abilities. However, the dominant two-stage pipeline (SFT then RL) suffers from a key inconsistency: SFT enforces rigid imitation that suppresses exploration and induces forgetting, limiting RL's potential for improvements. We address this inefficiency with TRAPO (Trust-Region Adaptive Policy Optimization), a hybrid framework that interleaves SFT and RL within each training instance by optimizing SFT loss on expert prefixes and RL loss on the model's own completions, unifying external supervision and self-exploration. To stabilize training, we introduce Trust-Region SFT (TrSFT), which minimizes forward KL divergence inside a trust region but attenuates optimization outside, effectively shifting toward reverse KL and yielding stable, mode-seeking updates favorable for RL. An adaptive prefix-selection mechanism further allocates expert guidance based on measured utility. Experiments on five mathematical
reasoning benchmarks show that TRAPO consistently surpasses standard SFT, RL, and SFT-then-RL pipelines, as well as recent state-of-the-art approaches, establishing a strong new paradigm for
reasoning-enhanced LLMs.
Read the full abstract ▾
All authors Mingyu Su, Jian Guan, Yuxian Gu, Minlie Huang, Hongning Wang
Machine Learning · Cross-listed from cs.CL
Confidence-Credibility Aware Weighted Ensembles of Small LLMs Outperform Large LLMs in Emotion Detection
Menna Elgabry and Ali Hamdi
This paper introduces a confidence-weighted, credibility-aware ensemble framework for text-based
emotion detection, inspired by Condorcet's Jury
Theorem (CJT). Unlike conventional ensembles that often rely on homogeneous architectures, our approach combines architecturally diverse small
transformer-based large
language models (sLLMs) - BERT, RoBERTa, DistilBERT, DeBERTa, and ELECTRA, each fully fine-tuned for
emotion classification. To preserve error diversity, we minimize parameter convergence while taking advantage of the unique biases of each model. A dual-weighted voting mechanism integrates both global credibility (validation F1 score) and local confidence (instance-level probability) to dynamically weight model contributions. Experiments on the DAIR-AI
dataset demonstrate that our credibility-confidence ensemble achieves a macro F1 score of 93.5 percent, surpassing state-of-the-art
benchmarks and significantly outperforming large-scale LLMs, including Falcon, Mistral, Qwen, and Phi, even after task-specific Low-Rank Adaptation (LoRA). With only 595M parameters in total, our small LLMs ensemble proves more parameter-efficient and robust than models up to 7B parameters, establishing that carefully designed ensembles of small, fine-tuned models can outperform much larger LLMs in specialized natural
language processing (NLP) tasks such as
emotion detection.
Read the full abstract ▾
Machine Learning
SCOPE: Sequential Causal Optimization of Process Interventions
Jakob De Moor, Hans Weytjens, Johannes De Smedt et al. (+1 more)
Prescriptive Process Monitoring (PresPM) recommends interventions during running business processes to optimize key performance indicators (KPIs). In realistic settings, interventions are rarely isolated: organizations need to align sequences of interventions to jointly steer the outcome of a case. Existing PresPM approaches only partially address this challenge. Many focus on a single intervention decision, while others treat multiple interventions independently, ignoring how they interact over time. Methods that do address these dependencies depend either on simulation or data augmentation to approximate the process to train a Reinforcement Learning (RL)
agent, which may create a reality gap and introduce bias. We introduce SCOPE (Sequential Causal Optimization of Process Interventions), a PresPM approach that learns aligned sequential intervention recommendations. SCOPE employs backward induction to estimate the effect of each candidate intervention action, propagating its impact from the final decision point back to the first. By leveraging causal learners, our method can utilize observational data directly, unlike methods that require constructing process approximations for RL. Experiments on both an existing synthetic
dataset and a new semi-synthetic
dataset show that SCOPE consistently outperforms state-of-the-art PresPM techniques in optimizing the KPI. The novel semi-synthetic setup, based on a real-life event log, is provided as a reusable
benchmark for future work on sequential PresPM.
Read the full abstract ▾
All authors Jakob De Moor, Hans Weytjens, Johannes De Smedt, Jochen De Weerdt
Machine Learning
More Consistent Accuracy PINN via Alternating Easy-Hard Training
Zhaoqian Gao and Min Yanga
Physics-informed neural networks (PINNs) have recently emerged as a prominent paradigm for solving partial differential equations (PDEs), yet their training strategies remain underexplored. While hard prioritization methods inspired by finite element methods are widely adopted, recent research suggests that easy prioritization can also be effective. Nevertheless, we find that both approaches exhibit notable trade-offs and inconsistent performance across PDE types. To address this issue, we develop a hybrid strategy that combines the strengths of hard and easy prioritization through an alternating training
algorithm. On PDEs with steep gradients, nonlinearity, and high dimensionality, the proposed method achieves consistently high accuracy, with relative L2 errors mostly in the range of O(10^-5) to O(10^-6), significantly surpassing baseline methods. Moreover, it offers greater reliability across diverse problems, whereas compared approaches often suffer from variable accuracy depending on the PDE. This work provides new insights into designing hybrid training strategies to enhance the performance and robustness of PINNs.
Read the full abstract ▾
Machine Learning
A Systems-Theoretic View on the Convergence of Algorithms under Disturbances
Guner Dilsad Er, Sebastian Trimpe and Michael Muehlebach
Algorithms increasingly operate within complex physical, social, and engineering systems where they are exposed to disturbances, noise, and interconnections with other dynamical systems. This article extends known convergence guarantees of an
algorithm operating in isolation (i.e., without disturbances) and systematically derives stability bounds and convergence rates in the presence of such disturbances. By leveraging converse Lyapunov
theorems, we derive key inequalities that quantify the impact of disturbances. We further demonstrate how our result can be utilized to assess the effects of disturbances on algorithmic performance in a wide variety of applications, including communication constraints in distributed learning, sensitivity in machine learning generalization, and intentional noise injection for
privacy. This underpins the role of our result as a unifying tool for
algorithm analysis in the presence of noise, disturbances, and interconnections with other dynamical systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
MAD-OOD: A Deep Learning Cluster-Driven Framework for an Out-of-Distribution Malware Detection and Classification
Tosin Ige, Christopher Kiekintveld, Aritran Piplai et al. (+3 more)
Out of distribution (OOD) detection remains a critical challenge in malware classification due to the substantial intra family variability introduced by polymorphic and metamorphic malware variants. Most existing deep learning based malware detectors rely on closed world assumptions and fail to adequately model this intra class variation, resulting in degraded performance when confronted with previously unseen malware families. This paper presents MADOOD, a novel two stage, cluster driven deep learning framework for robust OOD malware detection and classification. In the first stage, malware family
embeddings are modeled using class conditional spherical decision boundaries derived from Gaussian Discriminant Analysis (GDA), enabling statistically grounded separation of indistribution and OOD samples without requiring OOD data during training. Z score based distance analysis across multiple class centroids is employed to reliably identify anomalous samples in the latent space. In the second stage, a deep neural network integrates cluster based predictions, refined
embeddings, and supervised classifier outputs to enhance final classification accuracy. Extensive evaluations on
benchmark malware
datasets comprising 25 known families and multiple novel OOD variants demonstrate that MADOOD significantly outperforms state of the art OOD detection methods, achieving an AUC of up to 0.911 on unseen malware families. The proposed framework provides a scalable, interpretable, and statistically principled solution for real world malware detection and anomaly identification in evolving cybersecurity environments.
Read the full abstract ▾
All authors Tosin Ige, Christopher Kiekintveld, Aritran Piplai, Asif Rahman, Olukunle Kolade, Sasidhar Kunapuli
Machine Learning
A Unified Representation of Neural Networks Architectures
Christophe Prieur, Mircea Lazar and Bogdan Robu
In this paper we consider the limiting case of neural networks (NNs) architectures when the number of
neurons in each hidden layer and the number of hidden layers tend to infinity thus forming a continuum, and we derive approximation errors as a function of the number of
neurons and/or hidden layers. Firstly, we consider the case of neural networks with a single hidden layer and we derive an integral infinite width neural representation that generalizes existing continuous neural networks (CNNs) representations. Then we extend this to deep residual CNNs that have a finite number of integral hidden layers and residual connections. Secondly, we revisit the relation between neural ODEs and deep residual NNs and we formalize approximation errors via discretization techniques. Then, we merge these two approaches into a unified homogeneous representation of NNs as a Distributed Parameter neural Network (DiPaNet) and we show that most of the existing finite and infinite-dimensional NNs architectures are related via homogenization/discretization with the DiPaNet representation. Our approach is purely deterministic and applies to general, uniformly continuous
matrix weight functions. Relations with neural fields and other neural integro-differential equations are discussed along with further possible generalizations and applications of the DiPaNet framework.
Read the full abstract ▾
Machine Learning
Sharing Knowledge without Sharing Data: Stitches can improve ensembles of disjointly trained models
Arthur Guijt, Dirk Thierens, Ellen Kerkhof et al. (+3 more)
Deep learning has been shown to be very capable at performing many real-world tasks. However, this performance is often dependent on the presence of large and varied
datasets. In some settings, like in the medical domain, data is often fragmented across parties, and cannot be readily shared. While
federated learning addresses this situation, it is a solution that requires synchronicity of parties training a single model together, exchanging information about model weights. We investigate how asynchronous collaboration, where only already trained models are shared (e.g. as part of a publication), affects performance, and propose to use stitching as a method for combining models. Through taking a multi-objective perspective, where performance on each parties' data is viewed independently, we find that training solely on a single parties' data results in similar performance when merging with another parties' data, when considering performance on that single parties' data, while performance on other parties' data is notably worse. Moreover, while an ensemble of such individually trained networks generalizes better, performance on each parties' own
dataset suffers. We find that combining intermediate representations in individually trained models with a well placed pair of stitching layers allows this performance to recover to a competitive degree while maintaining improved generalization, showing that asynchronous collaboration can yield competitive results.
Read the full abstract ▾
All authors Arthur Guijt, Dirk Thierens, Ellen Kerkhof, Jan Wiersma, Tanja Alderliesten, Peter A.N. Bosman
Machine Learning
Learning Safe Autonomous Driving Policies Using Predictive Safety Representations
Mahesh Keswani and Raunak Bhattacharyya
Safe reinforcement learning (SafeRL) is a prominent paradigm for autonomous driving, where
agents are required to optimize performance under strict safety requirements. This dual objective creates a fundamental tension, as overly conservative policies limit driving efficiency while aggressive exploration risks safety violations. The Safety Representations for Safer Policy Learning (SRPL) framework addresses this challenge by equipping
agents with a predictive model of future constraint violations and has shown promise in controlled environments. This paper investigates whether SRPL extends to real-world autonomous driving scenarios. Systematic experiments on the Waymo Open Motion
Dataset (WOMD) and NuPlan demonstrate that SRPL can improve the reward-safety tradeoff, achieving statistically significant improvements in success rate (effect sizes r = 0.65-0.86) and cost reduction (effect sizes r = 0.70-0.83), with p < 0.05 for observed improvements. However, its effectiveness depends on the underlying policy optimizer and the
dataset distribution. The results further show that predictive safety representations play a critical role in improving robustness to observation noise. Additionally, in zero-shot cross-
dataset evaluation, SRPL-augmented
agents demonstrate improved generalization compared to non-SRPL methods. These findings collectively demonstrate the potential of predictive safety representations to strengthen SafeRL for autonomous driving.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.IV
SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis
N. A. Adarsh Pritam, Jeba Shiney O and Sanyam Jain
This work introduces SkinGenBench, a systematic biomedical imaging
benchmark that investigates how preprocessing complexity interacts with generative model choice for synthetic dermoscopic image augmentation and downstream melanoma diagnosis. Using a curated
dataset of $14,116$ dermoscopic images from HAM10000 and MILK10K across five lesion classes, we evaluate the two representative generative paradigms: StyleGAN2-ADA and Denoising
Diffusion Probabilistic Models (DDPMs) under basic
geometric augmentation and advanced artifact removal pipelines. Synthetic melanoma images are assessed using established perceptual and distributional metrics (FID, KID, IS), feature space analysis, and their impact on diagnostic performance across five downstream classifiers. Experimental results demonstrate that generative architecture choice has a stronger influence on both image fidelity and diagnostic utility than preprocessing complexity. StyleGAN2-ADA consistently produced synthetic images more closely aligned with real data distributions, achieving the lowest FID ($\approx 65.5$) and KID ($\approx 0.05$), while
diffusion models generated higher variance samples at the cost of reduced perceptual fidelity and class anchoring. Advanced artifact removal yielded only marginal improvements in generative metrics and provided limited downstream diagnostic gains, suggesting possible suppression of clinically relevant texture cues. In contrast, synthetic data augmentation substantially improved melanoma detection with $8$-$15$% absolute gains in melanoma F1-score, and ViT-B/16 achieving F1 $\approx 0.88$ and ROC-AUC $\approx 0.98$, representing an improvement of approximately $14\%$ over non-augmented baselines. Our code can be found at https://github.com/adarsh-crafts/SkinGenBench
Read the full abstract ▾
Machine Learning
Machine Learning for Static and Single-Event Dynamic Complex Network Analysis
Nikolaos Nakis
The primary objective of this thesis is to develop novel algorithmic approaches for Graph Representation Learning of static and single-event dynamic networks. In such a direction, we focus on the family of Latent Space Models, and more specifically on the Latent Distance Model which naturally conveys important network characteristics such as homophily, transitivity, and the balance theory. Furthermore, this thesis aims to create structural-aware network representations, which lead to hierarchical expressions of network structure, community characterization, the identification of extreme profiles in networks, and impact dynamics quantification in temporal networks. Crucially, the methods presented are designed to define unified learning processes, eliminating the need for heuristics and multi-stage processes like post-processing steps. Our aim is to delve into a journey towards unified network
embeddings that are both comprehensive and powerful, capable of characterizing network structures and adeptly handling the diverse tasks that graph analysis offers.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
Enabling Disaggregated Multi-Stage MLLM Inference via GPU-Internal Scheduling and Resource Sharing
Lingxiao Zhao, Haoran Zhou, Yuezhi Che et al. (+1 more)
Multimodal large
language models (MLLMs) extend LLMs with visual understanding through a three-stage pipeline:
multimodal preprocessing,
vision encoding, and LLM inference. While these stages enhance capability, they introduce significant system bottlenecks. First,
multimodal preprocessing-especially
video decoding-often dominates Time-to-First-
Token (TTFT). Most systems rely on CPU-based decoding, which severely limits throughput, while existing GPU-based approaches prioritize throughput-oriented parallelism and fail to meet the latency-sensitive requirements of MLLM inference. Second, the
vision encoder is a standalone, compute-intensive stage that produces visual
embeddings and cannot be co-batched with LLM prefill or decoding. This heterogeneity forces inter-stage blocking and increases
token-generation latency. Even when deployed on separate GPUs, these stages underutilize available compute and
memory resources, reducing overall utilization and constraining system throughput. To address these challenges, we present FlashCodec and UnifiedServe, two complementary designs that jointly optimize the end-to-end MLLM pipeline. FlashCodec accelerates the
multimodal preprocessing stage through collaborative multi-GPU
video decoding, reducing decoding latency while preserving high throughput. UnifiedServe optimizes the
vision-to-text and inference stages using a logically decoupled their execution to eliminate inter-stage blocking, yet physically sharing GPU resources to maximize GPU system utilization. By carefully orchestrating execution across stages and minimizing interference, UnifiedServe Together, our proposed framework forms an end-to-end optimized stack that can serve up to 3.0$\times$ more requests or enforce 1.5$\times$ tighter SLOs, while achieving up to 4.4$\times$ higher throughput compared to state-of-the-art systems.
Read the full abstract ▾
All authors Lingxiao Zhao, Haoran Zhou, Yuezhi Che, Dazhao Cheng
Machine Learning
GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping
Yishu Yin and Xuehai Qian
SSD-offloaded training offers a practical and promising approach to making LLM training cost-effective. Building on gradient accumulation with micro-batches, this paper introduces GreedySnake, a new SSD-offloaded training system that employs vertical scheduling, which executes all microbatches of a layer before proceeding to the next. Compared to existing systems that use horizontal scheduling (i.e., executing micro-batches sequentially), GreedySnake achieves higher training throughput with smaller batch sizes, bringing the system much closer to the ideal scenario predicted by the roofline model. To further mitigate the I/O bottleneck, GreedySnake overlaps part of the optimization step with the forward pass of the next iteration. Experimental results on A100 GPUs show that GreedySnake achieves saturated training throughput improvements over ZeRO-Infinity: 1.96x on 1 GPU and 1.93x on 4 GPUs for GPT-65B, and 2.53x on 1 GPU for GPT-175B.
Read the full abstract ▾
Machine Learning
Bayesian Optimisation: Which Constraints Matter?
Xietao Wang Lin, Juan Ungredda, Max Butler et al. (+4 more)
Bayesian optimisation has proven to be a powerful tool for expensive global black-box optimisation problems. In this paper, we propose new
Bayesian optimisation variants of the popular Knowledge Gradient acquisition functions for problems with decoupled black-box constraints, in which subsets of the objective and constraint functions may be evaluated independently. In particular, our methods aim to take into account that often only a handful of the constraints may be binding at the optimum, and hence we should evaluate only relevant constraints when trying to optimise a function. We empirically
benchmark these methods against existing methods and demonstrate their superiority over the state-of-the-art.
Read the full abstract ▾
All authors Xietao Wang Lin, Juan Ungredda, Max Butler, James Town, Alma Rahat, Hemant Singh, Juergen Branke
Machine Learning · Cross-listed from cs.SD
When De-noising Hurts: A Systematic Study of Speech Enhancement Effects on Modern Medical ASR Systems
Sujal Chondhekar, Vasanth Murukuri, Rushabh Vasani et al. (+8 more)
Speech enhancement methods are commonly believed to improve the performance of automatic
speech recognition (ASR) in noisy environments. However, the effectiveness of these techniques cannot be taken for granted in the case of modern large-scale ASR models trained on diverse, noisy data. We present a systematic evaluation of MetricGAN-plus-voicebank denoising on four state-of-the-art ASR systems: OpenAI Whisper, NVIDIA Parakeet, Google Gemini Flash 2.0, Parrotlet-a using 500 medical
speech recordings under nine noise conditions. ASR performance is measured using semantic WER (semWER), a normalized word error rate (WER) metric accounting for domain-specific normalizations. Our results reveal a counterintuitive finding:
speech enhancement preprocessing degrades ASR performance across all noise conditions and models. Original noisy audio achieves lower semWER than enhanced audio in all 40 tested configurations (4 models x 10 conditions), with degradations ranging from 1.1% to 46.6% absolute semWER increase. These findings suggest that modern ASR models possess sufficient internal noise robustness and that traditional
speech enhancement may remove acoustic features critical for ASR. For practitioners deploying medical scribe systems in noisy clinical environments, our results indicate that preprocessing audio with noise reduction techniques might not just be computationally wasteful but also be potentially harmful to the transcription accuracy.
Read the full abstract ▾
All authors Sujal Chondhekar, Vasanth Murukuri, Rushabh Vasani, Sanika Goyal, Rajshree Badami, Anushree Rana, Sanjana SN, Karthik Pandia, Sulabh Katiyar, Neha Jagadeesh, Sankalp Gulati
Machine Learning · Cross-listed from physics.flu-dyn
The HydroGym Reinforcement Learning Platform for Fluid Dynamics
Christian Lagemann, Sajeda Mokbel, Miro Gondrum et al. (+18 more)
Modeling and controlling fluids is critical across science and engineering. Effective flow control can increase lift, reduce drag, enhance mixing, and attenuate noise, potentially unlocking new technologies. Yet controlling fluids is hard: the dynamics are high-dimensional, nonlinear, and multiscale. While reinforcement learning (RL) has recently succeeded in robotics and
protein folding through shared
benchmarks, fluid dynamics has resisted such progress: each controller is typically tuned to a single geometry and operating point, making results hard to accumulate, transfer, and compare. We introduce HydroGym, a solver-independent RL platform for flow control, and show that standardized infrastructure unlocks transferable control intelligence across flow regimes. HydroGym provides 61+ validated environments spanning laminar to turbulent flows, with systematic Reynolds number progressions up to Re=400,000 and Mach number variations in 2D and 3D. It supports diverse backends, including finite-volume, spectral-element, finite-element,
lattice-Boltzmann, and fully differentiable solvers for gradient-enhanced optimization. Across environments, RL
agents consistently discover robust control principles, such as boundary-layer manipulation, acoustic-feedback disruption, and wake reorganization, yielding drag reductions exceeding 90% in canonical configurations. Critically, we demonstrate zero-shot transfer:
agents trained only on a simplified channel flow achieve 38% friction-drag reduction on an unseen 3D wing section at chord Reynolds number Re=200,000 reducing exploration costs by four orders of magnitude versus direct on-wing optimization. This suggests RL
agents uncover essential physics rather than configuration-specific patterns, pointing toward generalizable control. HydroGym offers extensible, scalable community infrastructure for fluid dynamics, machine learning, and control research.
Read the full abstract ▾
All authors Christian Lagemann, Sajeda Mokbel, Miro Gondrum, Mario Rüttgers, Yuning Wang, Pol Suárez, Ludger Paehler, Deniz A. Bezgin, Aaron B. Buhendwa, Jared L. Callaham, Samuel Ahnert, Nicholas Zolman, Xiao Shao, Jean-Christophe Loiseau, Nikolaus Adams, Matthias Meinke, Wolfgang Schröder, Kai Lagemann, Esther Lagemann, Ricardo Vinuesa, Steven L. Brunton
Machine Learning
NetworkFF: Unified Layer Optimization in Forward-Only Neural Networks
Salar Beigzad
The Forward-Forward
algorithm eliminates backpropagation's
memory constraints and biological implausibility through dual forward passes with positive and negative data. However, conventional implementations suffer from critical inter-layer isolation, where layers optimize goodness functions independently without leveraging collective learning dynamics. This isolation constrains representational coordination and limits convergence efficiency in deeper architectures. This paper introduces Collaborative Forward-Forward (CFF) learning, extending the original
algorithm through inter-layer cooperation mechanisms that preserve forward-only computation while enabling global context integration. Our framework implements two collaborative paradigms: Fixed CFF (F-CFF) with constant inter-layer coupling and Adaptive CFF (A-CFF) with learnable collaboration parameters that evolve during training. The collaborative goodness function incorporates weighted contributions from all layers, enabling coordinated feature learning while maintaining
memory efficiency and biological plausibility. Comprehensive evaluation on MNIST and Fashion-MNIST demonstrates significant performance improvements over baseline Forward-Forward implementations. These findings establish inter-layer collaboration as a fundamental enhancement to Forward-Forward learning, with immediate applicability to neuromorphic computing architectures and energy-constrained AI systems.
Read the full abstract ▾
Machine Learning
SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals
Muhammad Haris Khan
Foundation models for
protein design raise concrete biosecurity risks, yet the community lacks a simple, reproducible baseline for sequence-level hazard screening that is explicitly evaluated under homology control and runs on commodity CPUs. We introduce SafeBench-Seq, a metadata-only, reproducible
benchmark and baseline classifier built entirely from public data (SafeProtein hazards and UniProt benigns) and interpretable features (global physicochemical descriptors and amino-acid composition). To approximate "never-before-seen" threats, we homology-cluster the combined
dataset at <=40% identity and perform cluster-level holdouts (no cluster overlap between train/test). We report discrimination (AUROC/AUPRC) and screening-operating points (TPR@1% FPR; FPR@95% TPR) with 95% bootstrap confidence intervals (n=200), and we provide calibrated probabilities via CalibratedClassifierCV (isotonic for Logistic Regression / Random Forest; Platt sigmoid for Linear SVM). We quantify probability quality using Brier score, Expected Calibration Error (ECE; 15 bins), and reliability diagrams. Shortcut susceptibility is probed via composition-preserving residue shuffles and length-/composition-only ablations. Empirically, random splits substantially overestimate robustness relative to homology-clustered evaluation; calibrated linear models exhibit comparatively good calibration, while tree ensembles retain slightly higher Brier/ECE. SafeBench-Seq is CPU-only, reproducible, and releases metadata only (accessions, cluster IDs, split labels), enabling rigorous evaluation without distributing hazardous sequences.
Read the full abstract ▾