Machine Learning
You Need Better Attention Priors
Elon Litman and Gabe Guo
We generalize the
attention mechanism by viewing it through the lens of Entropic Optimal Transport, revealing that standard
attention corresponds to a transport problem regularized by an implicit uniform prior. We introduce Generalized Optimal transport
Attention with Trainable priors (GOAT), a new
attention mechanism that replaces this naive assumption with a learnable, continuous prior. This prior maintains full compatibility with optimized kernels such as FlashAttention. GOAT also provides an EOT-based explanation of
attention sinks and materializes a solution for them, avoiding the representational trade-offs of standard
attention. Finally, by absorbing spatial information into the core
attention computation, GOAT learns an extrapolatable prior that combines the flexibility of learned positional
embeddings with the length generalization of fixed encodings.
Read the full abstract ▾
Machine Learning
Improving MoE Compute Efficiency by Composing Weight and Data Sparsity
Maciej Kilian, Oleg Mkrtchyan, Luke Zettlemoyer et al. (+2 more)
Mixture-of-Experts layers achieve compute efficiency through weight sparsity: each
token activates only a subset of experts. Data sparsity, where each expert processes only a subset of
tokens, offers a complementary axis. Expert-choice routing implements data sparsity directly but violates causality in autoregressive models, creating train-inference mismatch. We recover data sparsity within causal
token-choice MoE by leveraging zero-compute (null) experts within the routing pool. When a
token routes to null experts, those slots consume no compute. The standard load balancing objective trains the model to uniformly use all experts (real and null) therefore creating data sparsity in expectation without the causality violations. We evaluate on
vision-
language model training, where data heterogeneity is pronounced:
vision encoders produce many low-information
tokens while text
tokens are denser. At matched expected FLOPs, composing weight and data sparsity yields a more compute-efficient frontier than weight sparsity alone, with gains in training loss and downstream performance. The model learns implicit modality-aware allocation, routing
vision tokens to null experts more aggressively than text, without explicit modality routing.
Read the full abstract ▾
All authors Maciej Kilian, Oleg Mkrtchyan, Luke Zettlemoyer, Akshat Shrivastava, Armen Aghajanyan
Machine Learning · Cross-listed from stat.ML
Non-Stationary Functional Bilevel Optimization
Jason Bohne, Ieva Petrulionyte, Michael Arbel et al. (+2 more)
Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static offline settings and perform suboptimally in online, non-stationary scenarios. We propose SmoothFBO, the first
algorithm for non-stationary FBO with both theoretical guarantees and practical scalability. SmoothFBO introduces a time-smoothed
stochastic hypergradient
estimator that reduces variance through a window parameter, enabling stable outer-loop updates with sublinear regret. Importantly, the classical parametric bilevel case is a special reduction of our framework, making SmoothFBO a natural extension to online, non-stationary settings. Empirically, SmoothFBO consistently outperforms existing FBO methods in non-stationary hyperparameter optimization and model-based reinforcement learning, demonstrating its practical effectiveness. Together, these results establish SmoothFBO as a general, theoretically grounded, and practically viable foundation for bilevel optimization in online, non-stationary scenarios.
Read the full abstract ▾
All authors Jason Bohne, Ieva Petrulionyte, Michael Arbel, Julien Mairal, Paweł Polak
Machine Learning · Cross-listed from quant-ph
USDs: A universal stabilizer decoder framework using symmetry
Hoshitaro Ohnishi and Hideo Mukai
Quantum error correction is indispensable to achieving reliable
quantum computation. When
quantum information is encoded redundantly, a larger
Hilbert space is constructed using multiple physical
qubits, and the computation is performed within a designated subspace. When applying deep learning to the decoding of
quantum error-correcting codes, a key challenge arises from the non-uniqueness between the syndrome measurements provided to the decoder and the corresponding error patterns that constitute the ground-truth labels. Building upon prior work that addressed this issue for the toric code by re-optimizing the decoder with respect to the
symmetry inherent in the parity-check structure, we generalize this approach to arbitrary stabilizer codes. In our experiments, we employed multilayer perceptrons to approximate continuous functions that complement the syndrome measurements of the Color code and the Golay code. Using these models, we performed decoder re-optimization for each code. For the Color code, we achieved an improvement of approximately 0.8% in decoding accuracy at a physical error rate of 5%, while for the Golay code the accuracy increased by about 0.1%. Furthermore, from the evaluation of the
geometric and algebraic structures in the continuous function approximation for each code, we showed that the design of generalized continuous functions is advantageous for learning the
geometric structure inherent in the code. Our results also indicate that approximations that faithfully reproduce the code structure can have a significant impact on the effectiveness of reoptimization. This study demonstrates that the re-optimization technique previously shown to be effective for the Toric code can be generalized to address the challenge of label degeneracy that arises when applying deep learning to the decoding of stabilizer codes.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Robust X-Learner: Breaking the Curse of Imbalance and Heavy Tails via Robust Cross-Imputation
Eichi Uehara
Estimating Heterogeneous Treatment Effects (HTE) in industrial applications such as AdTech and healthcare presents a dual challenge: extreme class imbalance and heavy-tailed outcome distributions. While the X-Learner framework effectively addresses imbalance through cross-imputation, we demonstrate that it is fundamentally vulnerable to "Outlier Smearing" when reliant on Mean Squared Error (MSE) minimization. In this failure mode, the bias from a few extreme observations ("whales") in the minority group is propagated to the entire majority group during the imputation step, corrupting the estimated treatment effect structure. To resolve this, we propose the Robust X-Learner (RX-Learner). This framework integrates a redescending {\gamma}-divergence objective – structurally equivalent to the Welsch loss under Gaussian assumptions – into the gradient boosting machinery. We further stabilize the non-convex optimization using a Proxy Hessian strategy grounded in Majorization-Minimization (MM) principles. Empirical evaluation on a semi-synthetic Criteo Uplift
dataset demonstrates that the RX-Learner reduces the Precision in Estimation of Heterogeneous Effect (PEHE) metric by 98.6% compared to the standard X-Learner, effectively decoupling the stable "Core" population from the volatile "Periphery".
Read the full abstract ▾
Machine Learning · Cross-listed from stat.AP
Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions
Asim H. Gazi, Yongyi Guo, Daiqi Gao et al. (+3 more)
Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural
language processing. Despite these advances, a substantial gap remains between RL research and its deployment in many practical settings. Two recurring challenges often underlie this gap. First, many settings offer limited opportunity for the
agent to interact extensively with the target environment due to practical constraints. Second, many target environments often undergo substantial changes, requiring redesign and redeployment of RL systems (e.g., advancements in science and technology that change the landscape of healthcare delivery). Addressing these challenges and bridging the gap between basic research and application requires theory and methodology that directly inform the design, implementation, and continual improvement of RL systems in real-world settings. In this paper, we frame the application of RL in practice as a three-component process: (i) online learning and optimization during deployment, (ii) post- or between-deployment offline analyses, and (iii) repeated cycles of deployment and redeployment to continually improve the RL system. We provide a narrative review of recent advances that address the statistical challenges arising across these three components, including methods for enhancing sample efficiency during online deployment, maximizing data utility for post- or between-deployment inference, and designing sequences of deployments for continual improvement. We also outline future research directions in RL that are use-inspired – aiming for impactful application of RL in practice.
Read the full abstract ▾
All authors Asim H. Gazi, Yongyi Guo, Daiqi Gao, Ziping Xu, Kelly W. Zhang, Susan A. Murphy
Machine Learning · Cross-listed from cs.AI
Logic Programming on Knowledge Graph Networks And its Application in Medical Domain
Chuanqing Wang, Zhenmin Zhao, Shanshan Du et al. (+3 more)
The rash development of knowledge graph research has brought big driving force to its application in many areas, including the medicine and healthcare domain. However, we have found that the application of some major information processing techniques on knowledge graph still lags behind. This defect includes the failure to make sufficient use of advanced logic
reasoning, advanced artificial intelligence techniques, special-purpose programming
languages, modern probabilistic and statistic theories et al. on knowledge graphs development and application. In particular, the multiple knowledge graphs cooperation and competition techniques have not got enough
attention from researchers. This paper develops a systematic theory, technique and application of the concept 'knowledge graph network' and its application in medical and healthcare domain. Our research covers its definition, development,
reasoning, computing and application under different conditions such as unsharp, uncertain, multi-modal, vectorized, distributed,
federated. Almost in each case we provide (real data) examples and experiment results. Finally, a conclusion of innovation is provided.
Read the full abstract ▾
All authors Chuanqing Wang, Zhenmin Zhao, Shanshan Du, Chaoqun Fei, Songmao Zhang, Ruqian Lu
Machine Learning · Cross-listed from cs.CV
Iterative Refinement Improves Compositional Image Generation
Shantanu Jaiswal, Mihir Prabhudesai, Nikash Bhardwaj et al. (+5 more)
Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex
prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as parallel sampling with verifiers or simply increasing denoising steps, can improve
prompt alignment but remain inadequate for richly compositional settings where many constraints must be satisfied. Inspired by the success of chain-of-thought
reasoning in large
language models, we propose an iterative test-time strategy in which a T2I model progressively refines its generations across multiple steps, guided by feedback from a
vision-
language model as the critic in the loop. Our approach is simple, requires no external tools or priors, and can be flexibly applied to a wide range of image generators and
vision-
language models. Empirically, we demonstrate consistent gains on image generation across
benchmarks: a 16.9% improvement in all-correct rate on ConceptMix (k=7), a 13.8% improvement on T2I-CompBench (3D-Spatial category) and a 12.5% improvement on Visual Jenga scene decomposition compared to compute-matched parallel sampling. Beyond quantitative gains, iterative refinement produces more faithful generations by decomposing complex
prompts into sequential corrections, with human evaluators preferring our method 58.7% of the time over 41.3% for the parallel baseline. Together, these findings highlight iterative self-correction as a broadly applicable principle for compositional image generation. Results and visualizations are available at https://iterative-img-gen.github.io/
Read the full abstract ▾
All authors Shantanu Jaiswal, Mihir Prabhudesai, Nikash Bhardwaj, Zheyang Qin, Amir Zadeh, Chuan Li, Katerina Fragkiadaki, Deepak Pathak
Machine Learning
MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs
Christoph Bartmann, Johannes Schimunek, Mykyta Ielanskyi et al. (+3 more)
A molecule's properties are fundamentally determined by its composition and structure encoded in its molecular graph. Thus,
reasoning about molecular properties requires the ability to parse and understand the molecular graph. Large
Language Models (LLMs) are increasingly applied to chemistry, tackling tasks such as molecular name conversion, captioning, text-guided generation, and property or reaction prediction. Most existing
benchmarks emphasize general chemical knowledge, rely on literature or surrogate labels that risk leakage or bias, or reduce evaluation to multiple-choice questions. We introduce MolecularIQ, a molecular structure
reasoning benchmark focused exclusively on symbolically verifiable tasks. MolecularIQ enables fine-grained evaluation of
reasoning over molecular graphs and reveals capability patterns that localize model failures to specific tasks and molecular structures. This provides actionable insights into the strengths and limitations of current chemistry LLMs and guides the development of models that reason faithfully over molecular structure.
Read the full abstract ▾
All authors Christoph Bartmann, Johannes Schimunek, Mykyta Ielanskyi, Philipp Seidl, Günter Klambauer, Sohvi Luukkonen
Machine Learning · Cross-listed from cs.CV
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
Yu Wu, Minsik Jeon, Jen-Hao Rick Chang et al. (+2 more)
We study positional encodings for multi-view
transformers that process
tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant
attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene. We find that prior (absolute or relative) encoding schemes for multi-view
attention do not meet these desiderata, and present RayRoPE to address this gap. RayRoPE represents patch positions based on associated rays and computes query-frame projective coordinates to ensure SE(3) invariance. To adapt to scene geometry, RayRoPE predicts (without direct supervision) a per-
token depth to obtain its position along the corresponding ray, while also modeling uncertainty and analytically computing the expected positional encoding. We validate our method on the tasks of novel-view synthesis, stereo depth estimation, and feed-forward 3DGS reconstruction. While remaining efficient, RayRoPE consistently improves over alternate position encoding schemes (e.g., 24% relative improvement on LPIPS in RE10K).
Read the full abstract ▾
All authors Yu Wu, Minsik Jeon, Jen-Hao Rick Chang, Oncel Tuzel, Shubham Tulsiani
Machine Learning · Cross-listed from stat.ML
Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible?
Felix Schur, Niklas Pfister, Peng Ding et al. (+2 more)
We study the problem of estimating causal effects under hidden confounding in the following unpaired data setting: we observe some
covariates $X$ and an outcome $Y$ under different experimental conditions (environments) but do not observe them jointly; we either observe $X$ or $Y$. Under appropriate regularity conditions, the problem can be cast as an instrumental variable (IV) regression with the environment acting as a (possibly high-dimensional) instrument. When there are many environments but only a few observations per environment, standard two-sample IV
estimators fail to be consistent. We propose a GMM-type
estimator based on cross-fold sample splitting of the instrument-
covariate sample and prove that it is consistent as the number of environments grows but the sample size per environment remains constant. We further extend the method to sparse causal effects via $\ell_1$-regularized estimation and post-selection refitting.
Read the full abstract ▾
All authors Felix Schur, Niklas Pfister, Peng Ding, Sach Mukherjee, Jonas Peters
Machine Learning
Recommending Best Paper Awards for ML/AI Conferences via the Isotonic Mechanism
Garrett G. Wen, Buxin Su, Natalie Collina et al. (+2 more)
Machine learning and artificial intelligence conferences such as NeurIPS and ICML now regularly receive tens of thousands of submissions, posing significant challenges to maintaining the quality and consistency of the peer review process. This challenge is particularly acute for best paper awards, which are an important part of the peer review process, yet whose selection has increasingly become a subject of debate in recent years. In this paper, we introduce an author-assisted mechanism to facilitate the selection of best paper awards. Our method employs the Isotonic Mechanism for eliciting authors' assessments of their own submissions in the form of a ranking, which is subsequently utilized to adjust the raw review scores for optimal estimation of the submissions' ground-truth quality. We demonstrate that authors are incentivized to report truthfully when their utility is a convex additive function of the adjusted scores, and we validate this convexity assumption for best paper awards using publicly accessible review data of ICLR from 2019 to 2023 and NeurIPS from 2021 to 2023. Crucially, in the special case where an author has a single quota – that is, may nominate only one paper – we prove that truthfulness holds even when the utility function is merely nondecreasing and additive. This finding represents a substantial relaxation of the assumptions required in prior work. For practical implementation, we extend our mechanism to accommodate the common scenario of overlapping authorship. Finally, simulation results demonstrate that our mechanism significantly improves the quality of papers selected for awards.
Read the full abstract ▾
All authors Garrett G. Wen, Buxin Su, Natalie Collina, Zhun Deng, Weijie Su
Machine Learning · Cross-listed from stat.ML
Multi-context principal component analysis
Kexin Wang, Salil Bhate, João M. Pereira et al. (+3 more)
Principal component analysis (PCA) is a tool to capture factors that explain variation in data. Across domains, data are now collected across multiple contexts (for example, individuals with different diseases,
cells of different types, or words across texts). While the factors explaining variation in data are undoubtedly shared across subsets of contexts, no tools currently exist to systematically recover such factors. We develop multi-context principal component analysis (MCPCA), a theoretical and algorithmic framework that decomposes data into factors shared across subsets of contexts. Applied to gene expression, MCPCA reveals axes of variation shared across subsets of cancer types and an axis whose variability in tumor
cells, but not mean, is associated with lung cancer progression. Applied to contextualized word
embeddings from
language models, MCPCA maps stages of a debate on human nature, revealing a discussion between science and fiction over decades. These axes are not found by combining data across contexts or by restricting to individual contexts. MCPCA is a principled generalization of PCA to address the challenge of understanding factors underlying data across contexts.
Read the full abstract ▾
All authors Kexin Wang, Salil Bhate, João M. Pereira, Joe Kileel, Matylda Figlerowicz, Anna Seigal
Machine Learning · Cross-listed from cs.CV
Tracing 3D Anatomy in 2D Strokes: Can Projection-Derived Masks Replace 3D Segmentation for Cervical Spine Fracture Recognition?
Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury et al. (+3 more)
Cervical spine fractures require rapid and accurate diagnosis, yet automatic CT interpretation remains challenging as subtle injuries must be assessed across large 3D volumes. We ask whether full 3D vertebra
segmentation is necessary for fracture recognition, or whether vertebra masks approximated from 2D projections preserve sufficient diagnostic context. In the proposed multi-stage pipeline, a YOLOv8 detector localizes the cervical spine from multi-view variance projections (3D mean Intersection over Union 94.45%). Multi-label vertebra
segmentation is performed with a DenseNet121-Unet on energy-based sagittal and coronal projections (mean Dice 87.86%). The predicted 2D masks are back-projected and fused into approximate 3D masks per vertebra to extract volumes of interest from the original CT, which are analyzed by an ensemble of 2.5D spatio-sequential CNN-
Transformer models. On the full RSNA 2022 cohort at native prevalence (2,019 patients, five-fold cross-validation), the pipeline yields vertebra-level and patient-level F1-scores of 68.15% and 82.28%, area under the receiver operating characteristic curve of 91.63% and 90.95%, and area under the precision-recall curve (AUPRC) of 75.64% and 92.00%. With the classifier architecture fixed, replacing 3D-
segmentation masks by projection-derived masks changed vertebra-level and patient-level AUPRC by +1.03 and +0.65 points, and the pipeline differed from the reproduced RSNA 2022 winning solution by -0.55 and +0.15 points. No AUPRC difference was statistically significant, and fold-wise 95% confidence intervals excluded vertebra-level losses larger than 1.46 and 2.81 points, respectively. Explainability and interobserver analyses examine reliability. Projection-based mask approximation is therefore a viable proxy for 3D vertebra
segmentation in cervical fracture recognition.
Read the full abstract ▾
All authors Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul
Machine Learning
ZENITH: Automated Gradient Norm Informed Stochastic Optimization
Dhrubo Saha
Training deep computer
vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational and
memory overhead, incompatibility with regularization, and suboptimal LR choices. In this work, we introduce the ZENITH (Zero-overhead
Evolution using Norm-Informed Training History) optimizer, which adapts the LR using the temporal
evolution of the gradient norm. Image classification experiments spanning 6 CNN architectures and 6
benchmarks demonstrate that ZENITH achieves higher test accuracy in lower wall-clock time than baselines. It also yielded superior mAP in object detection, keypoint detection, and instance
segmentation on MS COCO using the R-CNN family of models. Furthermore, its compatibility with regularization enables even better generalization.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
Zanlin Ni, Shenzhi Wang, Yang Yue et al. (+8 more)
Diffusion Large
Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling
token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior
reasoning potential. However, in this paper, we find that for general
reasoning tasks (e.g., mathematics and coding), arbitrary order generation may in fact limit the
reasoning potential of dLLMs. We observe that dLLMs tend to exploit this order flexibility to bypass high-uncertainty
tokens that are crucial for exploration, which can lead to a premature collapse of solution coverage. This observation motivates a rethink of RL approaches for dLLMs, where considerable complexities, such as handling combinatorial trajectories and intractable likelihoods, are often devoted to preserving this flexibility. We show that effective
reasoning can be elicited by simply forgoing arbitrary order and applying standard Group Relative Policy Optimization (GRPO) instead. Our approach, JustGRPO, is minimalist yet surprisingly effective (e.g., 89.1% accuracy on GSM8K) while fully retaining the parallel decoding ability of dLLMs. Project page: https://nzl-thu.github.io/the-flexibility-trap
Read the full abstract ▾
All authors Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, Cheng Yu, Bo Zheng, Gao Huang
Machine Learning
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
Yuval Ran-Milo, Yotam Alexander, Shahar Mendel et al. (+1 more)
Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate
reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy gradient to discover such systematic
reasoning remains poorly understood. We address this by analyzing the policy gradient dynamics of single-layer linear
Transformers on a synthetic graph traversal task that cannot be solved without Chain-of-Thought but admits a simple iterative solution. We prove that despite training solely on final-answer correctness, policy gradient drives the
Transformer to converge to a structured, interpretable
algorithm that iteratively traverses the graph vertex-by-vertex. We characterize the distributional properties required for this emergence, identifying the critical role of "simple examples": instances requiring fewer
reasoning steps. When the training distribution places sufficient mass on these simpler examples, the
Transformer learns a generalizable traversal strategy that extrapolates to longer chains; when this mass vanishes, policy gradient learning becomes infeasible. We corroborate our theoretical results through experiments on synthetic data and with real-world
language models on mathematical
reasoning tasks, validating that our theoretical findings carry over to practical settings.
Read the full abstract ▾
All authors Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen
Machine Learning
CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
Tianshi Xu, Yuteng Chen and Meng Li
Agentic Reinforcement Learning (RL) has empowered Large
Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B–7B), the exploration phase is often plagued by frequent execution failures, creating noisy trajectories that hinder policy optimization. Under standard outcome-based reward settings, this noise leads to a critical credit assignment issue, where erroneous actions are inadvertently reinforced alongside successful outcomes. Existing mitigations face a dilemma: dense rewards often trigger reward hacking, while supersampling incurs prohibitive computational costs. To address these challenges, we propose CLEANER. Distinct from external filtering methods, CLEANER exploits the model's intrinsic self-correction capabilities to eliminate error-contaminated context directly during data collection. At its core, the Similarity-Aware Adaptive Rollback (SAAR) mechanism autonomously constructs clean, purified trajectories by retrospectively replacing failures with successful self-corrections. Based on semantic similarity, SAAR adaptively regulates replacement granularity from shallow execution repairs to deep
reasoning substitutions. By training on these self-purified paths, the model internalizes correct
reasoning patterns rather than error-recovery loops. Empirical results on AIME24/25, GPQA, and LiveCodeBench show average accuracy gains of 6%, 3%, and 5% over baselines. Notably, CLEANER matches state-of-the-art performance using only one-third of the training steps, highlighting trajectory purification as a scalable solution for efficient agentic RL. Our models and code are available at GitHub
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Building Deep Graph Predictors with Graph Imitation Learning
André Eberhard, Gerhard Neumann and Pascal Friederich
Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the effectiveness of training neural networks with backpropagation and gradient descent. We argue that representing graphs on a fixed-size Euclidean grid, as is common in recently proposed models for supervised graph prediction, may not be the optimal choice in these settings. To support our view, we provide an analysis of neural graph generation methods and identify theoretical challenges that lead to pitfalls when training neural networks to produce graphs as their output. Motivated by this analysis, we introduce GRAph~Imitation~Learning~(GRAIL), a framework for training neural networks in supervised settings in which the supervision signal is a graph. GRAIL generates graphs sequentially through a Markov decision process over
embeddings of partial graphs, thereby avoiding the representation issues associated with fixed-size grid graph representations. We empirically show that GRAIL achieves competitive results on supervised graph prediction across a comprehensive suite of 18
benchmarks, matching or surpassing state-of-the-art methods in several settings.
Read the full abstract ▾
Machine Learning
DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training
Bostan Khan and Masoud Daneshtalab
Deploying
federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing
Federated Neural Architecture Search (FedNAS) methods suffer from unguided supernet training and prohibitively costly post-training search pipelines that validate thousands of subnets to construct learned accuracy predictors. We introduce DeepFedNAS, a two-phase framework built on a multi-objective fitness function that synthesizes information-theoretic network metrics with architectural heuristics. In the first phase,
Federated Pareto Optimal Supernet Training replaces random subnet sampling with a pre-computed cache of elite, high-fitness architectures, yielding a superior supernet. In the second phase, a Predictor-Free Search uses the structural fitness function as an accuracy proxy without constructing a learned subnet-accuracy predictor. In our CIFAR-10
benchmark, preparing the baseline predictor requires evaluating 10,000 subnets over the 5,000-image validation split, totaling 50 million image-level forward evaluations. DeepFedNAS eliminates these evaluations and selects a hardware-optimized architecture in $\sim$20 seconds on a CPU. Experiments on CIFAR-10, CIFAR-100, and CINIC-10 demonstrate state-of-the-art accuracy and robust performance under extreme non-IID conditions ($\alpha=0.1$). On CIFAR-100, DeepFedNAS provides an average 2.12-percentage-point gain across the four computation-budget intervals. Under the lowest evaluated computation budget, its mean result exceeds SuperFedNAS's best mean accuracy while using $2.95\times$ fewer parameters. These results make DeepFedNAS practical for scalable, communication-constrained IoT federations. Source code: https://github.com/bostankhan6/DeepFedNAS
Read the full abstract ▾
Machine Learning
RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation
Haonan Yuan, Qingyun Sun, Jiacheng Tao et al. (+2 more)
Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-
memory bottlenecks: they attempt to encode knowledge into model parameters, which limits semantic capacity, introduces heavy lossy compression with conflicts, and entangles graph representation with the knowledge in ways that hinder efficient adaptation, undermining scalability and interpretability. In this work,we propose RAG-GFM, a
Retrieval-Augmented Generation aided Graph Foundation Model that offloads knowledge from parameters and complements parameterized learning. To externalize graph knowledge, we build a dual-modal unified
retrieval module, where a semantic store from prefix-structured text and a structural store from centrality-based motif. To preserve heterogeneous information, we design a dual-view
alignment objective that contrasts both modalities to capture both content and relational patterns. To enable efficient downstream adaptation, we perform in-context augmentation to enrich supporting instances with retrieved texts and motifs as contextual evidence. Extensive experiments on five
benchmark graph
datasets demonstrate that RAG-GFM consistently outperforms 13 state-of-the-art baselines in both cross-domain node and graph classification, achieving superior effectiveness and efficiency.
Read the full abstract ▾
All authors Haonan Yuan, Qingyun Sun, Jiacheng Tao, Xingcheng Fu, Jianxin Li
Machine Learning · Cross-listed from cs.SD
WavLink: Compact Audio-Text Embeddings with a Global Whisper Token
Gokul Karthik Kumar, Ludovick Lepauloux and Hakim Hacid
Whisper has become the de-facto encoder for extracting general-purpose audio features in large audio-
language models, where a 30-second clip is typically represented by 1500 frame features projected into an LLM. In contrast, audio-text
embedding models like CLAP-based models have largely relied on alternative audio encoders (e.g., HTS-AT, PaSST), and have not leveraged Whisper effectively. We present WavLink, a compact audio-text
embedding model that augments Whisper encoder with a learnable global
token, trained jointly with a text encoder. Through a systematic study of design choices, including pretrained text encoders, loss functions, training modes, and data mixtures, we identify configurations that yield state-of-the-art
retrieval performance. Our two-stage training recipe across three model sizes, combined with Matryoshka-style supervision, improves scalability, enabling 8x smaller
embeddings with minimal performance drop. WavLink also demonstrates competitive performance on AIR-Bench with MCQs and zero-shot classification.
Read the full abstract ▾
Machine Learning
Auditing Language Model Unlearning via Information Decomposition
Anmol Goel, Alan Ritter and Iryna Gurevych
We expose a critical limitation in current approaches to machine unlearning in
language models: despite the apparent success of unlearning
algorithms, information about the forgotten data remains linearly decodable from internal representations. To systematically assess this discrepancy, we introduce an interpretable, information-theoretic framework for
auditing unlearning using Partial Information Decomposition (PID). By comparing model representations before and after unlearning, we decompose the mutual information with the forgotten data into distinct components, formalizing the notions of unlearned and residual knowledge. Our analysis reveals that redundant information, shared across both models, constitutes residual knowledge that persists post-unlearning and correlates with susceptibility to known
adversarial reconstruction attacks. Leveraging these insights, we propose a representation-based risk score that can guide abstention on sensitive inputs at inference time, providing a practical mechanism to mitigate
privacy leakage. Our work introduces a principled, representation-level audit for unlearning, offering theoretical insight and actionable tools for safer deployment of
language models.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.bio-ph
One scale to rule them all: interpretable multi-scale Deep Learning for predicting cell survival after proton and carbon ion irradiation
Giulio Bordieri, Giorgio Cartechini, Anna Bianchi et al. (+4 more)
The relationship between the physical characteristics of the radiation field and biological damage is central to both radiotherapy and radioprotection, yet the link between spatial scales of energy deposition and biological effects remains not entirely understood. To address this, we developed an interpretable deep learning model that predicts
cell survival after
proton and carbon ion irradiation, leveraging sequential
attention to highlight relevant features and provide insight into the contribution of different energy deposition scales. Trained and tested on the PIDE
dataset, our model incorporates, beside LET, nanodosimetric and microdosimetric quantities simulated with MC-Startrack and Open-TOPAS, enabling multi-scale characterization. While achieving high predictive accuracy, our approach also emphasizes transparency in decision-making. We demonstrate high accuracy in predicting RBE for in vitro experiments. Multiple scales are utilized concurrently, with no single spatial scale being predominant. Quantities defined at smaller spatial domains generally have a greater influence, whereas the LET plays a lesser role.
Read the full abstract ▾
All authors Giulio Bordieri, Giorgio Cartechini, Anna Bianchi, Anna Selva, Valeria Conte, Marta Missiaggia, Francesco G. Cordoni
Machine Learning
Field-Space Autoencoder for Scalable Climate Emulators
Johannes Meuer, Maximilian Witte, Étiénne Plésiat et al. (+2 more)
Kilometer-scale Earth system models are essential for capturing local
climate change. However, these models are computationally expensive and produce petabyte-scale outputs, which limits their utility for applications such as probabilistic risk assessment. Here, we present the Field-Space Autoencoder, a scalable
climate emulation framework based on a spherical compression model that overcomes these challenges. By utilizing Field-Space
Attention, the model efficiently operates on native
climate model output and therefore avoids
geometric distortions caused by forcing spherical data onto Euclidean grids. This approach preserves physical structures significantly better than convolutional baselines. By producing a structured compressed field, it serves as a good baseline for downstream generative emulation. In addition, the model can perform zero-shot super-resolution that maps low-resolution large ensembles and scarce high-resolution data into a shared representation. We train a generative
diffusion model on these compressed fields. The model can simultaneously learn internal variability from abundant low-resolution data and fine-scale physics from sparse high-resolution data. Our work bridges the gap between the high volume of low-resolution ensemble statistics and the scarcity of high-resolution physical detail.
Read the full abstract ▾
All authors Johannes Meuer, Maximilian Witte, Étiénne Plésiat, Thomas Ludwig, Christopher Kadow
Machine Learning
Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning
Oleg Shchendrigin, Egor Cherepanov, Alexey K. Kovalev et al. (+1 more)
Effective decision-making in the real world depends on
memory that is both stable and adaptive: environments change over time, and
agents must retain relevant information over long horizons while also updating or overwriting outdated content when circumstances shift. Existing Reinforcement Learning (RL)
benchmarks and
memory-augmented
agents focus primarily on retention, leaving the equally critical ability of
memory rewriting largely unexplored. To address this gap, we introduce a
benchmark that explicitly tests continual
memory updating under partial observability, i.e. the natural setting where an
agent must rely on
memory rather than current observations, and use it to compare recurrent,
transformer-based, and structured
memory architectures. Our experiments reveal that classic recurrent models, despite their simplicity, demonstrate greater flexibility and robustness in
memory rewriting tasks than modern structured
memories, which succeed only under narrow conditions, and
transformer-based
agents, which often fail beyond trivial retention cases. These findings expose a fundamental limitation of current approaches and emphasize the necessity of
memory mechanisms that balance stable retention with adaptive updating. Our work highlights this overlooked challenge, introduces
benchmarks to evaluate it, and offers insights for designing future RL
agents with explicit and trainable forgetting mechanisms. Code: https://quartz-admirer.github.io/
Memory-Rewriting/
Read the full abstract ▾
All authors Oleg Shchendrigin, Egor Cherepanov, Alexey K. Kovalev, Aleksandr I. Panov
Machine Learning · Cross-listed from cs.SD
Bangla Music Genre Classification Using Bidirectional LSTMS
Muntakimur Rahaman, Md Mahmudul Hoque and Md Mehedi Hassain
Bangla music is enrich in its own music cultures. Now a days music genre classification is very significant because of the exponential increase in available music, both in digital and physical formats. It is necessary to index them accordingly to facilitate improved
retrieval. Automatically classifying Bangla music by genre is essential for efficiently locating specific pieces within a vast and diverse music library. Prevailing methods for genre classification predominantly employ conventional machine learning or deep learning approaches. This work introduces a novel music
dataset comprising ten distinct genres of Bangla music. For the task of audio classification, we utilize a recurrent neural network (RNN) architecture. Specifically, a Long Short-Term
Memory (LSTM) network is implemented to train the model and perform the classification. Feature extraction represents a foundational stage in audio data processing. This study utilizes Mel-Frequency Cepstral Coefficients (MFCCs) to transform raw audio waveforms into a compact and representative set of features. The proposed framework facilitates music genre classification by leveraging these extracted features. Experimental results demonstrate a classification accuracy of 78%, indicating the system's strong potential to enhance and streamline the organization of Bangla music genres.
Read the full abstract ▾
Machine Learning
LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training
Chenyu Liu, Haige Li and Luca Rossi
Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constrained environments. Compared to quantization in LLMs, quantizing graph features is more emphasized in GNNs. Inspired by the above, we propose to leverage
prompt learning, which manipulates the input data, to improve the performance of quantization-aware training (QAT) for GNNs. To mitigate the issue that prompting the node features alone can only make part of the quantized aggregation result optimal, we introduce Low-Rank Aggregation Prompting (LoRAP), which injects lightweight, input-dependent
prompts into each aggregated feature to optimize the results of quantized aggregations. Extensive evaluations on 4 leading QAT frameworks over 9 graph
datasets demonstrate that LoRAP consistently enhances the performance of low-bit quantized GNNs while introducing a minimal computational overhead.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Multi-Agent Constraint Factorization Reveals Latent Invariant Solution Structure
Christopher Scofield
Multi-
agent systems (MAS) composed of large
language models often exhibit improved problem-solving performance despite operating on identical information. In this work, we provide a formal explanation for this phenomenon grounded in operator theory and constrained optimization. We model each
agent as enforcing a distinct family of validity constraints on a shared solution state, and show that a MAS implements a factorized composition of constraint-enforcement operators. Under mild conditions, these dynamics converge to invariant solution sets defined by the intersection of
agent constraint sets. Such invariant structures are generally not dynamically accessible to a single
agent applying all constraints simultaneously, even when expressive capacity and information are identical. We extend this result from exact constraint enforcement to soft constraints via proximal operators, and apply the formalism to contemporary text-based dialog systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SE
SmartOracle – An Agentic Approach to Mitigate Noise in Differential Oracles
Srinath Srinivasan, Tim Menzies and Marcelo D'Amorim
Differential fuzzers detect bugs by executing identical inputs across distinct implementations of the same specification, such as JavaScript interpreters. Validating the outputs requires an oracle and for differential testing of JavaScript, these are constructed manually, making them expensive, time-consuming, and prone to false positives. Worse, when the specification evolves, this manual effort must be repeated. Inspired by the success of agentic systems in other SE domains, this paper introduces SmartOracle. SmartOracle decomposes the manual triage workflow into specialized Large
Language Model (LLM) sub-
agents. These
agents synthesize independently gathered evidence from terminal runs and targeted specification queries to reach a final verdict. For historical
benchmarks, SmartOracle achieves 0.84 recall with an 18% false positive rate. Compared to a sequential Gemini 2.5 Pro baseline, it improves triage accuracy while reducing analysis time by 4$\times$ and API costs by 10$\times$. In active fuzzing campaigns, SmartOracle successfully identified and reported previously unknown specification-level issues across major engines, including bugs in V8, JavaScriptCore, and GraalJS. The success of SmartOracle's agentic architecture on Javascript suggests it might be useful other software systems- a research direction we will explore in future work.
Read the full abstract ▾