Machine Learning · Cross-listed from cs.IR
Image Complexity-Aware Adaptive Retrieval for Efficient Vision-Language Models
Mikel Williams-Lekuona and Georgina Cosma
Vision transformers in
vision-
language models typically use the same amount of compute for every image, regardless of whether it is simple or complex. We propose ICAR (Image Complexity-Aware
Retrieval), an adaptive computation approach that enables
vision transformers to use less compute for simple images whilst processing complex images through their full network depth. The key challenge is maintaining cross-modal
alignment:
embeddings from different processing depths must remain compatible for text matching. ICAR solves this through dual-path training that produces compatible
embeddings from both the early-exit and full-depth paths. This maintains compatibility between image representations and text
embeddings in the same semantic space, whether an image exits early or processes fully. Unlike existing two-stage approaches that require expensive reranking, ICAR enables direct image-text matching without additional overhead. To determine how much compute to use, we develop ConvNeXt-IC, which treats image complexity assessment as a classification task. By applying modern classifier backbones rather than specialised architectures, ConvNeXt-IC achieves state-of-the-art performance, attaining a Pearson correlation coefficient of 0.959 with human labelling whilst delivering 4.4x faster complexity prediction. Evaluated on standard
benchmarks augmented with real-world web data, ICAR achieves 20% faster image encoding while maintaining category-level performance and 95% of instance-level performance, enabling sustainable scaling of
vision-
language systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
Shiran Ge, Chenyi Huang, Yuang Ai et al. (+3 more)
Group Relative Policy Optimization (GRPO) is a powerful technique for aligning generative models, but its effectiveness is bottlenecked by the conflict between large group sizes and prohibitive computational costs. In this work, we investigate the trade-off through empirical studies, yielding two key observations. First, we discover the reward clustering phenomenon in which many trajectories collapse toward the group-mean reward, offering limited optimization value. Second, we design a heuristic strategy named Optimal Variance Filtering (OVF), and verify that a high-variance subset of trajectories, selected by OVF can outperform the larger, unfiltered group. However, this static, post-sampling OVF approach still necessitates critical computational overhead, as it performs unnecessary sampling for trajectories that are ultimately discarded. To resolve this, we propose Pro-GRPO (Proactive GRPO), a novel dynamic framework that integrates latent feature-based trajectory
pruning into the sampling process. Through the early termination of reward-clustered trajectories, Pro-GRPO reduces computational overhead. Leveraging its efficiency, Pro-GRPO employs an "Expand-and-Prune" strategy. This strategy first expands the size of initial sampling group to maximize trajectory diversity, then it applies multi-step OVF to the latents, avoiding prohibitive computational costs. Extensive experiments on both
diffusion-based and flow-based models demonstrate the generality and effectiveness of our Pro-GRPO framework.
Read the full abstract ▾
All authors Shiran Ge, Chenyi Huang, Yuang Ai, Qihang Fan, Huaibo Huang, Ran He
Machine Learning
Empirical Investigation of the Impact of Phase Information on Fault Diagnosis of Rotating Machinery
Hiroyoshi Nagahama, Katsufumi Inoue, Masayoshi Todorokihara et al. (+1 more)
Predictive maintenance of rotating machinery increasingly relies on vibration signals, yet most learning-based approaches either discard phase during spectral feature extraction or use raw time-waveforms without explicitly leveraging phase information. This paper introduces two phase-aware preprocessing strategies to address random phase variations in multi-axis vibration data: (1) three-axis independent phase adjustment that aligns each axis individually to zero phase (2) single-axis reference phase adjustment that preserves inter-axis relationships by applying uniform time shifts. Using a newly constructed rotor
dataset acquired with a synchronized three-axis sensor, we evaluate six deep learning architectures under a two-stage learning framework. Results demonstrate architecture-independent improvements: the three-axis independent method achieves consistent gains (+2.7% for
Transformer), while the single-axis reference approach delivers superior performance with up to 96.2% accuracy (+5.4%) by preserving spatial phase relationships. These findings establish both phase
alignment strategies as practical and scalable enhancements for predictive maintenance systems.
Read the full abstract ▾
All authors Hiroyoshi Nagahama, Katsufumi Inoue, Masayoshi Todorokihara, Michifumi Yoshioka
Machine Learning
Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
Chenxiang Zhang, Tongxi Qu, Zhong Li et al. (+3 more)
Deep neural networks are widely deployed with quantization techniques to reduce
memory and computational costs by lowering the numerical precision of their parameters. While quantization alters model parameters and their outputs, existing
privacy analyses primarily focus on full-precision models, leaving a gap in understanding how bit-width reduction can affect
privacy leakage. We present the first systematic study of the
privacy-utility relationship in post-training quantization (PTQ), a versatile family of methods that can be applied to pretrained models without further training. Using membership inference attacks as our evaluation framework, we analyze three popular PTQ
algorithms-AdaRound, BRECQ, and OBC-across multiple precision levels (4-bit, 2-bit, and 1.58-bit) on CIFAR-10, CIFAR-100, and TinyImageNet
datasets. Our findings consistently show that low-precision PTQs can reduce
privacy leakage. In particular, lower-precision models demonstrate up to an order of magnitude reduction in membership inference vulnerability compared to their full-precision counterparts, albeit at the cost of decreased utility. Additional ablation studies on the 1.58-bit quantization level show that quantizing only the last layer at higher precision enables fine-grained control over the
privacy-utility trade-off. These results offer actionable insights for practitioners to balance efficiency, utility, and
privacy protection in real-world deployments.
Read the full abstract ▾
All authors Chenxiang Zhang, Tongxi Qu, Zhong Li, Tian Zhang, Jun Pang, Sjouke Mauw
Machine Learning · Cross-listed from cs.SD
Time-Varying Audio Effect Modeling by End-to-End Adversarial Training
Yann Bourdin, Pierrick Legrand and Fanny Roche
Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems. Unlike time-invariant effects, training models on devices with internal modulation typically requires the recording or extraction of control signals to ensure the time-
alignment required by standard loss functions. This paper introduces a Generative
Adversarial Network (GAN) framework to model such effects using only input-output audio recordings, without requiring a modulation signal extraction. We propose a convolutional-recurrent architecture trained via a two-stage strategy: an initial
adversarial phase allows the model to learn the distribution of the modulation behavior without strict phase constraints, followed by a supervised fine-tuning phase where a State Prediction Network (SPN) estimates the initial internal states required to synchronize the model with the target. Additionally, a new metric based on chirp-train signals is developed to quantify modulation accuracy. Experiments modeling a vintage hardware phaser demonstrate the method's ability to capture time-varying dynamics in a fully black-box context.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
LLMQ: Efficient Lower-Precision Pretraining for Consumer GPUs
Erik Schultheis and Dan Alistarh
We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized
language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are characterized by low
memory availability and slow communication compared to datacentre-grade GPUs. Consequently, we showcase a range of optimizations that target these bottlenecks, including activation checkpointing, offloading, and copy-engine based collectives. LLMQ is able to train or fine-tune a 7B model on a single 16GB mid-range gaming card, or a 32B model on a workstation equipped with 4 RTX 4090s. This is achieved while executing a standard 8-bit training pipeline, without additional algorithmic approximations, and maintaining FLOP utilization of around 50%. The efficiency of LLMQ rivals that of production-scale systems on much more expensive cloud-grade GPUs.
Read the full abstract ▾
Machine Learning
Quantum Machine Learning for Cybersecurity: A Taxonomy and Future Directions
Siva Sai, Ishika Goyal, Shubham Sharma et al. (+3 more)
The increasing number of cyber threats and rapidly evolving tactics, as well as the high volume of data in recent years, have caused classical machine learning, rules, and signature-based defence strategies to fail, rendering them unable to keep up. An alternative,
Quantum Machine Learning (QML), has recently emerged, making use of computations based on
quantum mechanics. It offers better encoding and processing of high-dimensional structures for certain problems. This survey provides a comprehensive overview of QML techniques relevant to the domain of security, such as
Quantum Neural Networks (QNNs),
Quantum Support Vector Machines (QSVMs), Variational
Quantum Circuits (VQCs), and
Quantum Generative
Adversarial Networks (QGANs), and discusses the contributions of this paper in relation to existing research in the field and how it improves over them. It also maps these methods across supervised, unsupervised, and generative learning paradigms, and to core cybersecurity tasks, including intrusion and anomaly detection, malware and botnet classification, and encrypted-traffic analytics. It also discusses their application in the domain of cloud computing security, where QML can enhance secure and scalable operations. Many limitations of QML in the domain of cybersecurity have also been discussed, along with the directions for addressing them.
Read the full abstract ▾
All authors Siva Sai, Ishika Goyal, Shubham Sharma, Sri Harshita Manuri, Vinay Chamola, Rajkumar Buyya
Machine Learning
Topological Metric for Unsupervised Embedding Quality Evaluation
Aleksei Shestov, Anton Klenitskiy, Daria Denisova et al. (+4 more)
Modern representation learning increasingly relies on unsupervised and self-supervised methods trained on large-scale unlabeled data. While these approaches achieve impressive generalization across tasks and domains, evaluating
embedding quality without labels remains an open challenge. In this work, we propose Persistence, a
topology-aware metric based on persistent homology that quantifies the
geometric structure and topological richness of
embedding spaces in a fully unsupervised manner. Unlike metrics that assume linear separability or rely on covariance structure, Persistence captures global and multi-scale organization. Empirical results across diverse domains show that Persistence consistently achieves top-tier correlations with downstream performance, outperforming existing unsupervised metrics and enabling reliable model and hyperparameter selection.
Read the full abstract ▾
All authors Aleksei Shestov, Anton Klenitskiy, Daria Denisova, Amurkhan Dzagkoev, Daniil Petrovich, Andrey Savchenko, Maksim Makarenko
Machine Learning · Cross-listed from cs.SI
Model inference for ranking from pairwise comparisons
Daniel Sánchez Catalina and George T. Cantwell
We consider the problem of ranking objects from noisy pairwise comparisons, for example, ranking tennis players from the outcomes of matches. We follow a standard approach to this problem and assume that each object has an unobserved strength and that the outcome of each comparison depends probabilistically on the strengths of the comparands. However, we do not assume to know a priori how skills affect outcomes. Instead, we present an efficient
algorithm for simultaneously inferring both the unobserved strengths and the function that maps strengths to probabilities. Despite this problem being under-constrained, we present experimental evidence that the conclusions of our
Bayesian approach are robust to different model specifications. We include several case studies to exemplify the method on real-world data sets.
Read the full abstract ▾
Machine Learning
Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory
Huiyan Xue, Xuming Ran, Yaxin Li et al. (+4 more)
Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed
Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks via Top-K activation and have shown resilience against catastrophic forgetting. However, their rigid modularity limits cross-task knowledge reuse and leads to performance degradation under high sparsity. We propose Selective Subnetwork
Distillation (SSD), a structurally guided continual learning framework that treats
distillation not as a regularizer but as a
topology-aligned information conduit. SSD identifies
neurons with high activation frequency and selectively distills knowledge within previous Top-K subnetworks and output logits, without requiring replay or task labels. This enables structural realignment while preserving sparse modularity. Experiments on Split CIFAR-10, CIFAR-100, and MNIST demonstrate that SSD improves accuracy, retention, and representation coverage, offering a structurally grounded solution for sparse continual learning.
Read the full abstract ▾
All authors Huiyan Xue, Xuming Ran, Yaxin Li, Qi Xu, Enhui Li, Yi Xu, Qiang Zhang
Machine Learning · Cross-listed from cs.CV
Assessing the Visual Enumeration Abilities of Specialized Counting Architectures and Vision-Language Models
Kuinan Hou, Jing Mi, Marco Zorzi et al. (+2 more)
Counting the number of items in a visual scene remains a fundamental yet challenging task in computer
vision. Traditional approaches to solving this problem rely on domain-specific counting architectures, which are trained using
datasets annotated with a predefined set of object categories. However, recent progress in creating large-scale
multimodal vision-
language models (VLMs) suggests that these domain-general architectures may offer a flexible alternative for open-set object counting. In this study, we therefore systematically compare the performance of state-of-the-art specialized counting architectures against VLMs on two popular counting
datasets, as well as on a novel
benchmark specifically created to have a finer-grained control over the visual properties of test images. Our findings show that most VLMs can approximately enumerate the number of items in a visual scene, matching or even surpassing the performance of specialized computer
vision architectures. Notably, enumeration accuracy significantly improves when VLMs are prompted to generate intermediate representations (i.e., locations and verbal labels) of each object to be counted. Nevertheless, none of the models can reliably count the number of objects in complex visual scenes, showing that further research is still needed to create AI systems that can reliably deploy counting procedures in realistic environments.
Read the full abstract ▾
All authors Kuinan Hou, Jing Mi, Marco Zorzi, Lamberto Ballan, Alberto Testolin
Machine Learning
Leveraging Foundational Models and Simple Fusion for Multi-modal Physiological Signal Analysis
Youssef Ghallab, Omar Iraqy, Mohamed Kandil et al. (+5 more)
Physiological signals such as electrocardiograms (ECG) and electroencephalograms (
EEG) provide complementary insights into human health and cognition, yet multi-modal integration is challenging due to limited multi-modal labeled data, and modality-specific differences . In this work, we adapt the CBraMod encoder for large-scale self-supervised ECG pretraining, introducing a dual-masking strategy to capture intra- and inter-lead dependencies. To overcome the above challenges, we utilize a pre-trained CBraMod encoder for
EEG and pre-train a symmetric ECG encoder, equipping each modality with a rich foundational representation. These representations are then fused via simple
embedding concatenation, allowing the classification head to learn cross-modal interactions, together enabling effective downstream learning despite limited multi-modal supervision. Evaluated on
emotion recognition, our approach achieves near state-of-the-art performance, demonstrating that carefully designed physiological encoders, even with straightforward fusion, substantially improve downstream performance. These results highlight the potential of foundation-model approaches to harness the holistic nature of physiological signals, enabling scalable, label-efficient, and generalizable solutions for healthcare and affective computing.
Read the full abstract ▾
All authors Youssef Ghallab, Omar Iraqy, Mohamed Kandil, Mohamed Ashraf, Saadeldine Eletter, Morougue Ghazal, Ayman Khalafallah, Nagwa El-Makky
Machine Learning · Cross-listed from hep-ex
ColliderML: The First Release of an OpenDataDetector High-Luminosity Physics Benchmark Dataset
Doğa Elitez, Paul Gessinger, Daniel Murnane et al. (+5 more)
We introduce ColliderML - a large, open, experiment-agnostic
dataset of fully simulated and digitised
proton-
proton collisions in High-Luminosity Large
Hadron Collider conditions ($\sqrt{s}=14$ TeV, mean pile-up $\mu = 200$). ColliderML provides one million events across ten Standard Model and Beyond Standard Model processes, plus extensive single-particle samples, all produced with modern next-to-leading order
matrix element calculation and showering, realistic per-event pile-up overlay, a validated OpenDataDetector geometry, and standard reconstructions. The release fills a major gap for machine learning (ML) research on detector-level data, provided on the ML-friendly Hugging Face platform. We present physics coverage and the generation, simulation, digitisation and reconstruction pipeline, describe format and access, and initial
collider physics
benchmarks.
Read the full abstract ▾
All authors Doğa Elitez, Paul Gessinger, Daniel Murnane, Marcus Selchou Raaholt, Andreas Salzburger, Stine Kofoed Skov, Andreas Stefl, Anna Zaborowska
Machine Learning
O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization
Elio Gruttadauria, Mathieu Fontaine, Jonathan Le Roux et al. (+1 more)
We introduce O-EENC-SD: an end-to-end online speaker diarization system based on EEND-EDA, featuring a novel RNN-based stitching mechanism for online prediction. In particular, we develop a novel centroid refinement decoder whose usefulness is assessed through a rigorous ablation study. Our system provides key advantages over existing methods: a hyperparameter-free solution compared to unsupervised clustering approaches, and a more efficient alternative to current online end-to-end methods, which are computationally costly. We demonstrate that O-EENC-SD is competitive with the state of the art in the two-speaker conversational telephone
speech domain, as tested on the CallHome
dataset. Our results show that O-EENC-SD provides a great trade-off between DER and complexity, even when working on independent chunks with no overlap, making the system extremely efficient.
Read the full abstract ▾
All authors Elio Gruttadauria, Mathieu Fontaine, Jonathan Le Roux, Slim Essid
Machine Learning
Accelerating High-Throughput Catalyst Screening by Direct Generation of Equilibrium Adsorption Structures
Songze Huo and Xiao-Ming Cao
The adsorption energy serves as a crucial descriptor for the large-scale screening of catalysts. Nevertheless, the limited distribution of training data for the extensively utilised machine learning interatomic potential (MLIP), predominantly sourced from near-
equilibrium structures, results in unreliable adsorption structures and consequent adsorption energy predictions. In this context, we present DBCata, a deep generative model that integrates a periodic Brownian-bridge framework with an equivariant graph neural network to establish a low-dimensional transition
manifold between unrelaxed and DFT-relaxed structures, without requiring explicit energy or force information. Upon training, DBCata effectively generates high-fidelity adsorption geometries, achieving an interatomic distance mean absolute error (DMAE) of 0.035 \textÅ on the Catalysis-Hub
dataset, which is nearly three times superior to that of the current state-of-the-art machine learning potential models. Moreover, the corresponding DFT accuracy can be improved within 0.1 eV in 94% of instances by identifying and refining anomalous predictions through a hybrid chemical-heuristic and self-supervised outlier detection approach. We demonstrate that the remarkable performance of DBCata facilitates accelerated high-throughput computational screening for efficient
alloy catalysts in the oxygen reduction reaction, highlighting the potential of DBCata as a powerful tool for catalyst design and optimisation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DS
Label-consistent clustering for evolving data
Ameet Gadekar, Aristides Gionis and Thibault Marette
Data analysis often involves an iterative process, where solutions must be continuously refined in response to new data. Typically, as new data becomes available, an existing solution must be updated to incorporate the latest information. In addition to seeking a high-quality solution for the task at hand, it is also crucial to ensure consistency by minimizing drastic changes from previous solutions. Applying this approach across many iterations, ensures that the solution evolves gradually and smoothly. In this paper, we study the above problem in the context of clustering, specifically focusing on the $k$-center problem. More precisely, we study the following problem: Given a set of points $X$, parameters $k$ and $b$, and a prior clustering solution $H$ for $X$, our goal is to compute a new solution $C$ for $X$, consisting of $k$ centers, which minimizes the clustering cost while introducing at most $b$ changes from $H$. We refer to this problem as label-consistent $k$-center, and we propose two constant-factor approximation
algorithms for it. We complement our theoretical findings with an experimental evaluation demonstrating the effectiveness of our methods on real-world
datasets.
Read the full abstract ▾
Machine Learning
Chorus: Harmonizing Context and Sensing Signals for Data-Free Model Customization in IoT
Liyu Zhang, Yejia Liu, Kwun Ho Liu et al. (+2 more)
A key bottleneck toward scalable IoT sensing is efficiently adapting trained AI models to new deployment conditions. Context shifts, such as changes in sensor placement or ambient environments, can substantially alter sensing patterns and degrade model performance. We present Chorus, a context-bridged, data-free post-deployment model customization approach that adapts sensing models to unseen contexts without requiring target-domain sensor data or post-deployment retraining. Chorus learns compact, transferable context representations and aligns them with the sensor latent space using unlabeled sensor-context pairs, bridging context generalization with sensing-data generalization. It then uses a lightweight gated prediction head to integrate context priors at inference and an adaptive caching mechanism to reuse context representations when no context shift is detected, reducing on-device overhead. Experiments on IMU sensing,
speech enhancement, and WiFi sensing under diverse context shifts show that Chorus outperforms state-of-the-art baselines by up to 20.2% in unseen contexts, achieves inference latency comparable to sensor-only deployment, and remains stable under continuous context transitions and varied context descriptions. A
video demonstration is available at https://youtu.be/yANTZsk0TVU.
Read the full abstract ▾
All authors Liyu Zhang, Yejia Liu, Kwun Ho Liu, Runxi Huang, Xiaomin Ouyang
Machine Learning · Cross-listed from cs.SD
BEAT2AASIST model with layer fusion for ESDD 2026 Challenge
Sanghyeok Chung, Eujin Kim, Donggun Kim et al. (+7 more)
Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale
benchmark for Environmental Sound Deepfake Detection (ESDD). We propose BEAT2AASIST which extends BEATs-AASIST by splitting BEATs-derived representations along frequency or channel dimension and processing them with dual AASIST branches. To enrich feature representations, we incorporate top-k
transformer layer fusion using concatenation, CNN-gated, and SE-gated strategies. In addition, vocoder-based data augmentation is applied to improve robustness against unseen spoofing methods. Experimental results on the official test sets demonstrate that the proposed approach achieves competitive performance across the challenge tracks.
Read the full abstract ▾
All authors Sanghyeok Chung, Eujin Kim, Donggun Kim, Gaeun Heo, Jeongbin You, Nahyun Lee, Sunmook Choi, Soyul Han, Seungsang Oh, Il-Youp Kwak
Machine Learning
DEER: Draft with Diffusion, Verify with Autoregressive Models
Zicong Cheng, Guo-Wei Yang, Jia Li et al. (+3 more)
Efficiency, as a critical practical challenge for LLM-driven agentic and
reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify scheme, yet existing approaches rely on AR draft models (a.k.a., drafters), which introduce two fundamental issues: (1) step-wise uncertainty accumulation leads to a progressive collapse of trust between the target model and the drafter, and (2) inherently sequential decoding of AR drafters. Together, these factors cause limited speedups. In this paper, we show that a
diffusion large
language model (dLLM) drafters can naturally overcome these issues through its fundamentally different probabilistic modeling and efficient parallel decoding strategy. Building on this insight, we introduce DEER, an efficient speculative decoding framework that drafts with
diffusion and verifies with AR models. To enable high-quality drafting, DEER employs a two-stage training pipeline to align the dLLM-based drafters with the target AR model, and further adopts single-step decoding to generate long draft segments. Experiments show DEER reaches draft acceptance lengths of up to 32
tokens, far surpassing the 10
tokens achieved by EAGLE-3. Moreover, on HumanEval with Qwen3-30B-A3B, DEER attains a 5.54x speedup, while EAGLE-3 achieves only 2.41x. Code, model, demo, etc, will be available at https://czc726.github.io/DEER/
Read the full abstract ▾
All authors Zicong Cheng, Guo-Wei Yang, Jia Li, Zhijie Deng, Meng-Hao Guo, Shi-Min Hu
Machine Learning
Understanding NTK Variance in Implicit Neural Representations
Chengguang Ou and Yixin Zhuang
Implicit Neural Representations (INRs) often converge slowly and struggle to recover high-frequency details due to spectral bias. While prior work links this behavior to the Neural Tangent Kernel (NTK), how specific architectural choices affect NTK conditioning remains unclear. We show that many INR mechanisms can be understood through their impact on a small set of pairwise similarity factors and scaling terms that jointly determine NTK
eigenvalue variance. For standard coordinate MLPs, limited input-feature interactions induce large
eigenvalue dispersion and poor conditioning. We derive closed-form variance decompositions for common INR components and show that positional encoding reshapes input similarity, spherical normalization reduces variance via layerwise scaling, and Hadamard modulation introduces additional similarity factors strictly below one, yielding multiplicative variance reduction. This unified view explains how diverse INR architectures mitigate spectral bias by improving NTK conditioning. Experiments across multiple tasks confirm the predicted variance reductions and demonstrate faster, more stable convergence with improved reconstruction quality.
Read the full abstract ▾
Machine Learning
An Efficient Gradient-Based Inference Attack for Federated Learning
Pablo Montaña-Fernández and Ines Ortega-Fernandez
Federated Learning is a machine learning setting that reduces direct data exposure, improving the
privacy guarantees of machine learning models. Yet, the exchange of model updates between the participants and the aggregator can still leak sensitive information. In this work, we present a new gradient-based membership inference attack for
federated learning scenarios that exploits the temporal
evolution of last-layer gradients across multiple
federated rounds. Our method uses the shadow technique to learn round-wise gradient patterns of the training records, requiring no access to the private
dataset, and is designed to consider both semi-honest and malicious adversaries (aggregators or data owners). Beyond membership inference, we also provide a natural extension of the proposed attack to discrete attribute inference by contrasting gradient responses under alternative attribute hypotheses. The proposed attacks are model-agnostic, and therefore applicable to any gradient-based model and can be applied to both classification and regression settings. We evaluate the attack on CIFAR-100 and Purchase100
datasets for membership inference and on Breast Cancer Wisconsin for attribute inference. Our findings reveal strong attack performance and comparable computational and
memory overhead in membership inference when compared to another attack from the literature. The obtained results emphasize that multi-round
federated learning can increase the vulnerability to inference attacks, that aggregators pose a more substantial threat than data owners, and that attack performance is strongly influenced by the nature of the training
dataset, with richer, high-dimensional data leading to stronger leakage than simpler tabular data.
Read the full abstract ▾
Machine Learning
Generalization and Feature Attribution in Machine Learning Models for Crop Yield and Anomaly Prediction in Germany
Roland Baatz
This study examines the generalization performance and interpretability of machine learning (ML) models used for predicting crop yield and yield anomalies in Germany's NUTS-3 regions. Using a high-quality, long-term
dataset, the study systematically compares the evaluation and temporal validation behavior of ensemble tree-based models (XGBoost, Random Forest) and deep learning approaches (LSTM, TCN). While all models perform well on spatially split, conventional test sets, their performance degrades substantially on temporally independent validation years, revealing persistent limitations in generalization. Notably, models with strong test-set accuracy, but weak temporal validation performance can still produce seemingly credible SHAP feature importance values. This exposes a critical vulnerability in post hoc explainability methods: interpretability may appear reliable even when the underlying model fails to generalize. These findings underscore the need for validation-aware interpretation of ML predictions in agricultural and environmental systems. Feature importance should not be accepted at face value unless models are explicitly shown to generalize to unseen temporal and spatial conditions. The study advocates for domain-aware validation, hybrid modeling strategies, and more rigorous scrutiny of explainability methods in data-driven agriculture. Ultimately, this work addresses a growing challenge in environmental data science: how can we evaluate generalization robustly enough to trust model explanations?
Read the full abstract ▾
Machine Learning
From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
Aaron Mueller, Andrew Lee, Shruti Joshi et al. (+3 more)
A goal of interpretability is to recover disentangled representations of latent concepts (features) from the activations of neural networks. The quality of features is typically evaluated in isolation, and under implicit independence assumptions that may not hold in practice. Thus, it is unclear to what extent common featurization methods such as sparse autoencoders (SAEs) and probes disentangle one concept from another. We propose a multi-concept evaluation setting using concepts including sentiment, domain, voice, and tense. We evaluate how well featurizers produce disentangled representations of each concept, observing that features are typically sensitive to only one concept, but also that concepts are distributed across many features. Then, we steer these features, measuring whether each concept is independently manipulable, and whether features interact. Even in idealized settings, steering a feature often affects many concepts, despite a near absence of interaction effects. These results suggest that correlational metrics are insufficient to establish steering selectivity, and that demonstrating that two features operate in separate spaces is insufficient to claim that they will be selective for one concept. These results underscore the importance of multi-concept evaluations in interpretability research.
Read the full abstract ▾
All authors Aaron Mueller, Andrew Lee, Shruti Joshi, Ekdeep Singh Lubana, Dhanya Sridhar, Patrik Reizinger
Machine Learning
Mukur Gupta, Niharika Gupta, Saifur Rahman et al. (+2 more)
Deep learning models deployed on edge devices are increasingly used in safety-critical applications. However, their vulnerability to
adversarial perturbations poses significant risks, especially in
Federated Learning (FL) settings where identical models are distributed across thousands of clients. While
adversarial training is a strong defense, it is difficult to apply in FL due to strict client-data
privacy constraints and the limited compute available on edge devices. In this work, we introduce TrajSyn, a
privacy-preserving framework that enables effective server-side
adversarial training by synthesizing a proxy
dataset from the trajectories of client model updates, without accessing raw client data. We show that TrajSyn consistently improves
adversarial robustness on image classification
benchmarks with no extra compute burden on the client device.
Read the full abstract ▾
All authors Mukur Gupta, Niharika Gupta, Saifur Rahman, Shantanu Pal, Chandan Karmakar
Machine Learning
Automatic Reward Shaping from Multi-Objective Human Heuristics
Yuqing Xie, Jiayu Chen, Wenhao Tang et al. (+3 more)
Designing effective reward functions remains a central challenge in reinforcement learning, especially in multi-objective environments. In this work, we propose Multi-Objective Reward Shaping with Exploration (MORSE), a general framework that automatically combines multiple human-designed heuristic rewards into a unified reward function. MORSE formulates the shaping process as a bi-level optimization problem: the inner loop trains a policy to maximize the current shaped reward, while the outer loop updates the reward function to optimize task performance. To encourage exploration in the reward space and avoid suboptimal local minima, MORSE introduces stochasticity into the shaping process, injecting noise guided by task performance and the prediction error of a fixed, randomly initialized neural network. Experimental results in MuJoCo and Isaac Sim environments show that MORSE effectively balances multiple objectives across various robotic tasks, achieving task performance comparable to those obtained with manually tuned reward functions.
Read the full abstract ▾
All authors Yuqing Xie, Jiayu Chen, Wenhao Tang, Ya Zhang, Chao Yu, Yu Wang
Machine Learning
FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
Runze Li, Hanchen Wang, Wenjie Zhang et al. (+4 more)
Multivariate time series imputation is fundamental in applications such as healthcare, traffic
forecasting, and biological modeling, where sensor failures and irregular sampling lead to pervasive missing values. Existing
Transformer- and
diffusion-based imputers achieve strong performance, but they often rely mainly on time-domain modeling and lack adaptive spectral bias for recovering structured temporal gaps. We propose FADTI, a
Fourier- and
attention-driven
diffusion framework for multivariate time series imputation. FADTI introduces a
Fourier Bias Projection (FBP) module that injects learnable frequency-aware bias into intermediate hidden states during denoising. It projects intermediate hidden states onto
Fourier bases, avoiding direct spectral estimation from masked or zero-filled inputs. With DFT, STFT, and FSST instantiations, FBP captures global periodicity, localized time–frequency variations, and non-stationary oscillatory patterns. By coupling FBP with self-
attention and gated convolution, FADTI integrates frequency-domain guidance, temporal dependency modeling, and probabilistic denoising in a unified framework. Experiments on multiple
benchmarks, including a new biological imputation
benchmark, show that FADTI improves accuracy, uncertainty estimation, and sampling efficiency, especially under high missing rates and structured missing patterns. Code is available at https://github.com/RazeenLI/FADTI
Read the full abstract ▾
All authors Runze Li, Hanchen Wang, Wenjie Zhang, Binghao Li, Yu Zhang, Xuemin Lin, Ying Zhang
Machine Learning
How Many Heads Make an SSM? A Unified Framework for Attention and State Space Models
Ali Ghodsi
Sequence modeling has produced diverse architectures – from classical recurrent neural networks to modern
Transformers and state space models (SSMs) – yet a unified theoretical understanding of expressivity and trainability trade-offs remains limited. We introduce a unified framework that represents a broad class of sequence maps via an input-dependent effective interaction operator $W_{ij}(X)$, making explicit two recurring construction patterns: (i) the Unified Factorized Framework (Explicit) (
attention-style mixing), in which $W_{ij}(X)$ varies through scalar coefficients applied to shared value maps, and (ii) Structured Dynamics (Implicit) (state-space recurrences), in which $W_{ij}$ is induced by a latent dynamical system. Using this framework, we derive three theoretical results. First, we establish the Interaction Rank Gap: models in the Unified Factorized Framework, such as single-head
attention, are constrained to a low-dimensional operator span and cannot represent certain structured dynamical maps. Second, we prove an Equivalence (Head-Count)
Theorem showing that, within our multi-head factorized class, representing a linear SSM whose lag operators span a $k$-dimensional subspace on length-$n$ sequences requires and is achievable with $H=k$ heads. Third, we prove a Gradient Highway Result, showing that
attention layers admit inputs with distance-independent gradient paths, whereas stable linear dynamics exhibit distance-dependent gradient attenuation. Together, these results formalize a fundamental trade-off between algebraic expressivity (interaction/operator span) and long-range gradient propagation, providing theoretical grounding for modern sequence architecture design.
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.CP
Adaptive Weighted Genetic Algorithm-Optimized SVR for Robust Long-Term Forecasting of Global Stock Indices for investment decisions
Mohit Beniwal
Long-term price
forecasting remains a formidable challenge due to the inherent uncertainty over the long term, despite some success in short-term predictions. Nonetheless, accurate long-term forecasts are essential for high-net-worth individuals, institutional investors, and traders. The proposed improved genetic
algorithm-optimized support vector regression (IGA-SVR) model is specifically designed for long-term price prediction of global indices. The performance of the IGA-SVR model is rigorously evaluated and compared against the state-of-the-art baseline models, the Long Short-Term
Memory (LSTM), and the forward-validating genetic
algorithm optimized support vector regression (OGA-SVR). Extensive testing was conducted on the five global indices, namely Nifty, Dow Jones Industrial Average (DJI), DAX Performance Index (DAX), Nikkei 225 (N225), and Shanghai Stock Exchange Composite Index (SSE) from 2021 to 2024 of daily price prediction up to a year. Overall, the proposed IGA-SVR model achieved a reduction in MAPE by 19.87% compared to LSTM and 50.03% compared to OGA-SVR, demonstrating its superior performance in long-term daily price
forecasting of global indices. Further, the execution time for LSTM was approximately 20 times higher than that of IGA-SVR, highlighting the high accuracy and computational efficiency of the proposed model. The genetic
algorithm selects the optimal hyperparameters of SVR by minimizing the arithmetic mean of the Mean Absolute Percentage Error (MAPE) calculated over the full training
dataset and the most recent five years of training data. This purposefully designed training methodology adjusts for recent trends while retaining long-term trend information, thereby offering enhanced generalization compared to the LSTM and rolling-forward validation approach employed by OGA-SVR, which forgets long-term trends and suffers from recency bias.
Read the full abstract ▾
Machine Learning
Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
Sunwoo Kim, Soo Yong Lee, Kyungho Kim et al. (+3 more)
Unsupervised node representation learning aims to obtain meaningful node
embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph
topology. However, excessive reliance on graph convolution can be suboptimal-especially in non-homophilic graphs-since it may yield unduly similar
embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the
embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14
benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.
Read the full abstract ▾
All authors Sunwoo Kim, Soo Yong Lee, Kyungho Kim, Hyunjin Hwang, Jaemin Yoo, Kijung Shin
Machine Learning
SigMA: Path Signatures and Multi-head Attention for Learning Parameters in fBm-driven SDEs
Xianglin Wu, Chiheb Ben Hammouda and Cornelis W. Oosterlee
Stochastic differential equations (SDEs) driven by fractional Brownian motion (fBm) are increasingly used to model systems with rough dynamics and long-range dependence, such as those arising in quantitative finance and reliability engineering. However, these processes are non-Markovian and lack a semimartingale structure, rendering many classical parameter estimation techniques inapplicable or computationally intractable beyond very specific cases. This work investigates two central questions: (i) whether integrating path signatures into deep learning architectures can improve the trade-off between estimation accuracy and model complexity, and (ii) what constitutes an effective architecture for leveraging signatures as feature maps. We introduce SigMA (Signature Multi-head
Attention), a neural architecture that integrates path signatures with multi-head self-
attention, supported by a convolutional preprocessing layer and a multilayer perceptron for effective feature encoding. SigMA learns model parameters from synthetically generated paths of fBm-driven SDEs, including fractional Brownian motion, fractional Ornstein-Uhlenbeck, and rough Heston models, with a particular focus on estimating the Hurst parameter and on joint multi-parameter inference, and it generalizes robustly to unseen trajectories. Extensive experiments on synthetic data and two real-world
datasets (i.e., equity-index realized
volatility and Li-ion battery degradation) show that SigMA consistently outperforms CNN, LSTM, vanilla
Transformer, and Deep Signature baselines in accuracy, robustness, and model compactness. These results demonstrate that combining signature transforms with
attention-based architectures provides an effective and scalable framework for parameter inference in
stochastic systems with rough or persistent temporal structure.
Read the full abstract ▾