Machine Learning · Cross-listed from cs.CV
Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and Critique
Zhehan Zhang, Meihua Qian, Li Luo et al. (+4 more)
Assessing artistic creativity is foundational to creativity research and arts education, yet manual scoring (e.g., Torrance Tests of Creative Thinking) is labor-intensive at scale. Prior machine-learning approaches show promise for visual creativity scoring, but many rely mainly on image features and provide limited or no explanatory feedback. We propose a framework for automated creativity assessment of human paintings by fine-tuning the
vision-
language model Qwen2-VL-7B with multi-task learning. Our
dataset contains 1000 human-created paintings scored on a 1-100 scale and paired with a short human-written description (content or artist explanation). Two expert raters evaluated each work using a five-dimension rubric (originality, color, texture, composition, content) and provided written critiques; we use an 80/20 train-test split. We add a lightweight regression head on the visual encoder output so the model can predict a numerical score and generate rubric-aligned feedback in a single forward pass. By
embedding the structured rubric and the artwork description in the system
prompt, we constrain the generated text to match the quantitative prediction. Experiments show strong accuracy, achieving Pearson r > 0.97 and MAE about 3.95 on the 100-point scale. Qualitative evaluation indicates the generated feedback is semantically close to expert critiques (average SBERT cosine similarity = 0.798). The proposed approach bridges computer
vision and art assessment and offers a scalable tool for creativity research and classroom feedback.
Read the full abstract ▾
All authors Zhehan Zhang, Meihua Qian, Li Luo, Siyu Huang, Chaoyi Zhou, Ripon Saha, Xinxin Song
Machine Learning · Cross-listed from cs.CV
Spectral Collapse in Diffusion Inversion
Nicolas Bourriez, Alexandre Verine and Auguste Genovesio
Conditional
diffusion inversion provides a powerful framework for unpaired image-to-image translation. However, we demonstrate through an extensive analysis that standard deterministic inversion (e.g. DDIM) fails when the source domain is spectrally sparse compared to the target domain (e.g., super-resolution, sketch-to-image). In these contexts, the recovered latent from the input does not follow the expected isotropic Gaussian distribution. Instead it exhibits a signal with lower frequencies, locking target sampling to oversmoothed and texture-poor generations. We term this phenomenon spectral collapse. We observe that
stochastic alternatives attempting to restore the noise variance tend to break the semantic link to the input, leading to structural drift. To resolve this structure-texture trade-off, we propose Orthogonal Variance Guidance (OVG), an inference-time method that corrects the ODE dynamics to enforce the theoretical Gaussian noise magnitude within the null-space of the structural gradient. Extensive experiments on microscopy super-resolution (BBBC021) and sketch-to-image (Edges2Shoes) demonstrate that OVG effectively restores photorealistic textures while preserving structural fidelity.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Conditional Generative Models for High-Resolution Range Profiles: Capturing Geometry-Driven Trends in a Large-Scale Maritime Dataset
Edwyn Brient, Santiago Velasco-Forero and Rami Kassab
High-resolution range profiles (HRRPs) enable fast onboard processing for radar automatic target recognition, but their strong sensitivity to acquisition conditions limits robustness across operational scenarios. Conditional HRRP generation can mitigate this issue, yet prior studies are constrained by small, highly specific
datasets. We study HRRP synthesis on a largescale maritime database representative of coastal surveillance variability. Our analysis indicates that the fundamental scenario drivers are
geometric: ship dimensions and the desired aspect angle. Conditioning on these variables, we train generative models and show that the synthesized signatures reproduce the expected line-of-sight
geometric trend observed in real data. These results highlight the central role of acquisition geometry for robust HRRP generation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
MFN Decomposition and Related Metrics for High-Resolution Range Profiles Generative Models
Edwyn Brient, Santiago Velasco-Forero and Rami Kassab
High-resolution range profile (HRRP ) data are in vogue in radar automatic target recognition (RATR). With the interest in classifying models using HRRP, filling gaps in
datasets using generative models has recently received promising contributions. Evaluating generated data is a challenging topic, even for explicit data like face images. However, the evaluation methods used in the state-ofthe-art of HRRP generation rely on classification models. Such models, called ”black-box”, do not allow either explainability on generated data or multi-level evaluation. This work focuses on decomposing HRRP data into three components: the mask, the features, and the noise. Using this decomposition, we propose two metrics based on the physical interpretation of those data. We take profit from an expensive
dataset to evaluate our metrics on a challenging task and demonstrate the discriminative ability of those.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Basic Legibility Protocols Improve Trusted Monitoring
Ashwin Sreevatsa, Sebastian Prasanna and Cody Rushing
The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human oversight is expensive, one approach is trusted monitoring, where weaker, trusted models oversee stronger, untrusted models$\unicode{x2013}$but this often fails when the untrusted model's actions exceed the monitor's comprehension. We introduce legibility protocols, which encourage the untrusted model to take actions that are easier for a monitor to evaluate. We perform control evaluations in the APPS coding setting, where an
adversarial agent attempts to write backdoored code without detection. We study legibility protocols that allow the untrusted model to thoroughly document its code with comments$\unicode{x2013}$in contrast to prior work, which removed comments to prevent deceptive ones. We find that: (i) commenting protocols improve safety without sacrificing task performance relative to comment-removal baselines; (ii) commenting disproportionately benefits honest code, which typically has a natural explanation that resolves monitor suspicion, whereas backdoored code frequently lacks an easy justification; (iii) gains from commenting increase with monitor strength, as stronger monitors better distinguish genuine justifications from only superficially plausible ones.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.GN
Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol
Zahra Khodagholi and Niloofar Yousefi
Saliency maps are increasingly used as design guidance in siRNA efficacy prediction, yet attribution methods are rarely validated before motivating sequence edits. We introduce a pre-synthesis gate: a protocol for counterfactual sensitivity faithfulness that tests whether mutating high-saliency positions changes model output more than composition-matched controls. Cross-
dataset transfer reveals two failure modes that would otherwise go undetected: faithful-but-wrong (saliency valid, predictions fail) and inverted saliency (top-saliency edits less impactful than random). Strikingly, models trained on mRNA-level assays collapse on a luciferase reporter
dataset, demonstrating that protocol shifts can silently invalidate deployment. Across four
benchmarks, 19/20 fold instances pass; the single failure shows inverted saliency. A biology-informed regularizer (BioPrior) strengthens saliency faithfulness with modest,
dataset-dependent predictive trade-offs. Our results establish saliency validation as essential pre-deployment practice for explanation-guided therapeutic design. Code is available at https://github.com/shadi97kh/BioPrior.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
When LLMs get significantly worse: A statistical approach to detect model degradations
Jonas Kübler, Kailash Budhathoki, Matthäus Kleindessner et al. (+4 more)
Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others without accuracy guarantees like quantization. In all of these cases it is crucial to ensure that the model quality has not degraded. However, even at temperature zero, model generations are not necessarily robust even to theoretically lossless model optimizations due to numerical errors. We thus require statistical tools to decide whether a finite-sample accuracy deviation is an evidence of a model's degradation or whether it can be attributed to (harmless) noise in the evaluation. We propose a statistically sound hypothesis testing framework based on McNemar's test allowing to efficiently detect model degradations, while guaranteeing a controlled rate of false positives. The crucial insight is that we have to confront the model scores on each sample, rather than aggregated on the task level. Furthermore, we propose three approaches to aggregate accuracy estimates across multiple
benchmarks into a single decision. We provide an implementation on top of the largely adopted open source LM Evaluation Harness and provide a case study illustrating that the method correctly flags degraded models, while not flagging model optimizations that are provably lossless. We find that with our tests even empirical accuracy degradations of 0.3% can be confidently attributed to actual degradations rather than noise.
Read the full abstract ▾
All authors Jonas Kübler, Kailash Budhathoki, Matthäus Kleindessner, Xiong Zhou, Junming Yin, Ashish Khetan, George Karypis
Machine Learning
The effect of whitening on explanation performance
Benedict Clark, Stoyan Karastoyanov, Rick Wilming et al. (+1 more)
Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a critical challenge. Prior research (Haufe et al., 2014; Wilming et al., 2022, 2023) has demonstrated that these methods often erroneously assign significant importance to non-informative variables, such as suppressor variables, leading to fundamental misinterpretations. Since statistical suppression is induced by feature dependencies, this study investigates whether data whitening, a common preprocessing technique for decorrelation, can mitigate such errors. Using the established XAI-TRIS
benchmark (Clark et al., 2024b), which offers synthetic ground-truth data and quantitative measures of explanation correctness, we empirically evaluate 16 popular feature attribution methods applied in combination with 5 distinct whitening transforms. Additionally, we analyze a minimal linear two-dimensional classification problem (Wilming et al., 2023) to theoretically assess whether whitening can remove the impact of suppressor features from Bayes-optimal models. Our results indicate that, while specific whitening techniques can improve explanation performance, the degree of improvement varies substantially across XAI methods and model architectures. These findings highlight the complex relationship between data non-linearities, preprocessing quality, and attribution fidelity, underscoring the vital role of pre-processing techniques in enhancing model interpretability.
Read the full abstract ▾
All authors Benedict Clark, Stoyan Karastoyanov, Rick Wilming, Stefan Haufe
Machine Learning · Cross-listed from stat.ML
Mutual Information Collapse Explains Disentanglement Failure in $\beta$-VAEs
Minh Vu, Xiaoliang Wan and Shuangqing Wei
The $\beta$-VAE is a foundational framework for unsupervised disentanglement, using $\beta$ to regulate the trade-off between latent factorization and reconstruction fidelity. Empirically, however, disentanglement performance exhibits a pervasive non-monotonic trend:
benchmarks such as MIG and SAP typically peak at intermediate $\beta$ and collapse as regularization increases. We demonstrate that this collapse is a fundamental information-theoretic failure, where strong Kullback-Leibler pressure promotes marginal independence at the expense of the latent channel's semantic informativeness. By formalizing this mechanism in a linear-Gaussian setting, we prove that for $\beta > 1$, stationarity-induced dynamics trigger a spectral contraction of the encoder gain, driving latent-factor mutual information to zero. To resolve this, we introduce the $\lambda\beta$-VAE, which decouples regularization pressure from informational collapse via an auxiliary $L_2$ reconstruction penalty $\lambda$. Extensive experiments on dSprites, Shapes3D, and MPI3D-real confirm that $\lambda > 0$ stabilizes disentanglement and restores latent informativeness over a significantly broader range of $\beta$, providing a principled theoretical justification for dual-parameter regularization in variational inference backbones.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Effective Reasoning Chains Reduce Intrinsic Dimensionality
Archiki Prasad, Mandar Joshi, Kenton Lee et al. (+2 more)
Chain-of-thought (CoT)
reasoning and its variants have substantially improved the performance of
language models on complex
reasoning tasks, yet the precise mechanisms by which different strategies facilitate generalization remain poorly understood. While current explanations often point to increased test-time computation or structural guidance, establishing a consistent, quantifiable link between these factors and generalization remains challenging. In this work, we identify intrinsic dimensionality as a quantitative measure for characterizing the effectiveness of
reasoning chains. Intrinsic dimensionality quantifies the minimum number of model dimensions needed to reach a given accuracy threshold on a given task. By keeping the model architecture fixed and varying the task formulation through different
reasoning strategies, we demonstrate that effective
reasoning strategies consistently reduce the intrinsic dimensionality of the task. Validating this on GSM8K with Gemma-3 1B and 4B, we observe a strong inverse correlation between the intrinsic dimensionality of a
reasoning strategy and its generalization performance on both in-distribution and out-of-distribution data. Our findings suggest that effective
reasoning chains facilitate learning by better compressing the task using fewer parameters, offering a new quantitative metric for analyzing
reasoning processes.
Read the full abstract ▾
All authors Archiki Prasad, Mandar Joshi, Kenton Lee, Mohit Bansal, Peter Shaw
Machine Learning
Generalizing GNNs with Tokenized Mixture of Experts
Xiaoguang Guo, Zehong Wang, Jiazheng Li et al. (+5 more)
Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations. We show that static inference induces a fundamental tradeoff: improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor. Instance-conditional routing can break this ceiling, but is fragile because shifts can mislead routing and perturbations can make routing fluctuate. We capture these effects via two decompositions separating coverage vs selection, and base sensitivity vs fluctuation amplification. Based on these insights, we propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths, a vector-quantized
token interface to stabilize encoder-to-head signals, and a Lipschitz-regularized head to bound output amplification. Across nine node, link, and graph
benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
Read the full abstract ▾
All authors Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel, Qi Yang, Kaize Ding, Jundong Li, Chuxu Zhang
Machine Learning · Cross-listed from math.ST
Optimal Estimation in Orthogonally Invariant Generalized Linear Models: Spectral Initialization and Approximate Message Passing
Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan et al. (+1 more)
We consider the problem of parameter estimation from a generalized linear model with a random design
matrix that is orthogonally invariant in law. Such a model allows the design have an arbitrary distribution of singular values and only assumes that its singular vectors are generic. It is a vast generalization of the i.i.d. Gaussian design typically considered in the theoretical literature, and is motivated by the fact that real data often have a complex correlation structure so that methods relying on i.i.d. assumptions can be highly suboptimal. Building on the paradigm of spectrally-initialized iterative optimization, this paper proposes optimal spectral
estimators and combines them with an approximate message passing (AMP)
algorithm, establishing rigorous performance guarantees for these two algorithmic steps. Both the spectral initialization and the subsequent AMP meet existing
conjectures on the fundamental limits to estimation – the former on the optimal sample complexity for efficient weak recovery, and the latter on the optimal errors. Numerical experiments suggest the effectiveness of our methods and accuracy of our theory beyond orthogonally invariant data.
Read the full abstract ▾
All authors Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan, Marco Mondelli
Machine Learning
Feature salience - not task-informativeness - drives machine learning model explanations
Benedict Clark, Marta Oliveira, Rick Wilming et al. (+1 more)
Explainable AI (XAI) promises to provide insight into machine learning models' decision processes, where one goal is to identify failures such as shortcut learning. This promise relies on the field's assumption that input features marked as important by an XAI must contain information about the target variable. However, it is unclear whether informativeness is indeed the main driver of importance attribution in practice, or if other data properties such as statistical suppression, novelty at test-time, or high feature salience substantially contribute. To clarify this, we trained deep learning models on three variants of a binary image classification task, in which translucent watermarks are either absent, act as class-dependent confounds, or represent class-independent noise. Results for five popular attribution methods show substantially elevated relative importance in watermarked areas (RIW) for all models regardless of the training setting ($R^2 \geq .45$). By contrast, whether the presence of watermarks is class-dependent or not only has a marginal effect on RIW ($R^2 \leq .03$), despite a clear impact impact on model performance and generalisation ability. XAI methods show similar behaviour to model-agnostic edge detection filters and attribute substantially less importance to watermarks when bright image intensities are encoded by smaller instead of larger feature values. These results indicate that importance attribution is most strongly driven by the salience of image structures at test time rather than statistical associations learned by machine learning models. Previous studies demonstrating successful XAI application should be reevaluated with respect to a possibly spurious concurrency of feature salience and informativeness, and workflows using feature attribution methods as building blocks should be scrutinised.
Read the full abstract ▾
All authors Benedict Clark, Marta Oliveira, Rick Wilming, Stefan Haufe
Machine Learning
RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdata
Matthias Templ, Oscar Thees and Roman Müller
Statistical data anonymization increasingly relies on fully synthetic microdata, for which classical identity disclosure measures are less informative than an adversary's ability to infer sensitive attributes from released data. We introduce RAPID (Risk of Attribute Prediction–Induced Disclosure), a disclosure risk measure that directly quantifies inferential vulnerability under a realistic attack model. An adversary trains a predictive model solely on the released synthetic data and applies it to real individuals' quasi-identifiers. For continuous sensitive attributes, RAPID reports the proportion of records whose predicted values fall within a specified relative error tolerance. For categorical attributes, we propose a baseline-normalized confidence score that measures how much more confident the attacker is about the true class than would be expected from class prevalence alone, and we summarize risk as the fraction of records exceeding a policy-defined threshold. This construction yields an interpretable, bounded risk metric that is robust to class imbalance, independent of any specific synthesizer, and applicable with arbitrary learning
algorithms. We illustrate threshold calibration, uncertainty quantification, and comparative evaluation of synthetic data generators using simulations and real data. Our results show that RAPID provides a practical, attacker-realistic upper bound on attribute-inference disclosure risk that complements existing utility diagnostics and disclosure control frameworks.
Read the full abstract ▾
Machine Learning
Do Neural Networks Lose Plasticity in a Gradually Changing World?
Tianhui Liu and Lili Mou
Continual learning has become a trending topic in machine learning. Recent studies have discovered an interesting phenomenon called loss of plasticity, referring to neural networks gradually losing the ability to learn new tasks. However, existing plasticity research largely relies on
benchmarks with abrupt task transitions, without examining whether the abruptness itself contributes to the observed plasticity loss. In this paper, we investigate the role of transition abruptness by simulating gradually changing environments through input/output interpolation and task sampling. We perform theoretical and empirical analysis, showing that the severity of plasticity loss is closely tied to the abruptness of task transitions, and can be substantially reduced when the environment changes gradually.
Read the full abstract ▾
Machine Learning
When Does Embedding Magnitude Matter? A Cross-Task Functional-Symmetry Framework
Xincan Feng and Taro Watanabe
Cosine similarity normalizes both sides; dot product normalizes neither. We propose a 2x2 framework that independently controls query-side and document-side normalization, exposing two intermediate variants (QNorm, DNorm) that have not been previously studied. On
retrieval with four encoders, evaluated in-domain on MS MARCO and out-of-domain on BEIR, BRIGHT, and multi-hop QA, the unilateral variants outperform both cosine and dot product, with relative gains of up to +72% out-of-domain and +24% on downstream RAG. Cross-evaluation reveals the mechanism: document magnitude scales inference scores while query magnitude modulates training gradients, and the Fisher Information
Matrix condition number predicts which side to normalize. We then classify tasks by functional
symmetry, defined as whether the aggregate scoring procedure treats Q and C as interchangeable, and test whether the mechanism extends beyond
retrieval. On five additional task families (semantic textual similarity, CLIP, knowledge graph completion, few-shot classification, recommender systems), the coarse prediction (cosine for symmetric, magnitude-preserving for asymmetric) holds in every case examined; the unilateral variants beat Cosine on recommendation, and on few-shot classification DNorm beats both Cosine and the standard Euclidean default of Prototypical Networks.
Read the full abstract ▾
Machine Learning
Barycentric alignment for instance-level comparison of neural representations
Shreya Saha, Zoe Wanying He and Meenakshi Khosla
Comparing representations across neural networks is challenging because representations admit
symmetries, such as arbitrary reordering of units or rotations of activation space, that obscure underlying equivalence between models. We introduce a barycentric
alignment framework that quotients out these nuisance
symmetries to construct a universal
embedding space across many models. Unlike existing similarity measures, which summarize relationships over entire stimulus sets, this framework enables similarity to be defined at the level of individual stimuli, revealing inputs that elicit convergent versus divergent representations across models. Using this instance-level notion of similarity, we identify systematic input properties that predict representational convergence versus divergence across
vision and
language model families. We also construct universal
embedding spaces for
brain representations across individuals and cortical regions, enabling instance-level comparison of representational agreement across stages of the human visual hierarchy. Finally, we apply the same barycentric
alignment framework to purely unimodal
vision and
language models and find that post-hoc
alignment into a shared space yields image text similarity scores that closely track human cross-modal judgments and approach the performance of contrastively trained
vision-
language models. This strikingly suggests that independently learned representations already share sufficient
geometric structure for human-aligned cross-modal comparison. Together, these results show that resolving representational similarity at the level of individual stimuli reveals phenomena that cannot be detected by set-level comparison metrics.
Read the full abstract ▾
Machine Learning
A Lightweight Multi-View Approach to Short-Term Load Forecasting
Julien Guité-Vinet, Alexandre Blondin Massé and Éric Beaudry
Time series
forecasting is a critical task across domains such as energy, finance, and meteorology, where accurate predictions enable informed decision-making. While
transformer-based and large-parameter models have recently achieved state-of-the-art results, their complexity can lead to overfitting and unstable forecasts, especially when older data points become less relevant. In this paper, we propose a lightweight multi-view approach to short-term load
forecasting that leverages single-value
embeddings and a scaled time-range input to capture temporally relevant features efficiently. We introduce an
embedding dropout mechanism to prevent over-reliance on specific features and enhance interpretability. Our method achieves competitive performance with significantly fewer parameters, demonstrating robustness across multiple
datasets, including scenarios with noisy or sparse data, and provides insights into the contributions of individual features to the forecast.
Read the full abstract ▾
Machine Learning
CausalGDP: Causality-Guided Diffusion Policies for Reinforcement Learning
Xiaofeng Xiao, Xiao Hu, Yang Ye et al. (+1 more)
Reinforcement learning (RL) has achieved remarkable success in a wide range of sequential decision-making problems. Recent
diffusion-based policies further improve RL by modeling complex, high-dimensional action distributions. However, existing
diffusion policies primarily rely on statistical associations and fail to explicitly account for causal relationships among states, actions, and rewards, limiting their ability to identify which action components truly cause high returns. In this paper, we propose Causality-guided
Diffusion Policy (CausalGDP), a unified framework that integrates causal
reasoning into
diffusion-based RL. CausalGDP first learns a base
diffusion policy and an initial causal dynamical model from offline data, capturing causal dependencies among states, actions, and rewards. During real-time interaction, the causal information is continuously updated and incorporated as a guidance signal to steer the
diffusion process toward actions that causally influence future states and rewards. By explicitly considering causality beyond association, CausalGDP focuses policy optimization on action components that genuinely drive performance improvements. Experimental results demonstrate that CausalGDP consistently achieves competitive or superior performance over state-of-the-art
diffusion-based and offline RL methods, especially in complex, high-dimensional control tasks.
Read the full abstract ▾
All authors Xiaofeng Xiao, Xiao Hu, Yang Ye, Xubo Yue
Machine Learning · Cross-listed from eess.SY
EExApp: GNN-Based Reinforcement Learning for Radio Unit Energy Optimization in 5G O-RAN
Jie Lu, Peihao Yan and Huacheng Zeng
With over 3.5 million 5G base stations deployed globally, their collective energy consumption (projected to exceed 131 TWh annually) raises significant concerns over both operational costs and environmental impacts. In this paper, we present EExAPP, a deep reinforcement learning (DRL)-based xApp for 5G Open
Radio Access Network (O-RAN) that jointly optimizes
radio unit (RU) sleep scheduling and distributed unit (DU) resource slicing. EExAPP uses a dual-actor-dual-critic Proximal Policy Optimization (PPO) architecture, with dedicated actor-critic pairs targeting energy efficiency and quality-of-service (QoS) compliance. A
transformer-based encoder enables scalable handling of variable user equipment (UE) populations by encoding all-UE observations into fixed-dimensional representations. To coordinate the two optimization objectives, a bipartite Graph
Attention Network (GAT) is used to modulate actor updates based on both critic outputs, enabling adaptive trade-offs between power savings and QoS. We have implemented EExAPP and deployed it on a real-world 5G O-RAN testbed with live traffic, commercial RU and smartphones. Extensive over-the-air experiments and ablation studies confirm that EExAPP significantly outperforms existing methods in reducing the energy consumption of RU while maintaining QoS. The source code is available at https://github.com/EExApp/EExApp.
Read the full abstract ▾
Machine Learning
Fair Feature Importance Scores via Feature Occlusion and Permutation
Camille Little, Madeline Navarro, Santiago Segarra et al. (+1 more)
As machine learning models increasingly impact society, their opaque nature poses challenges to trust and accountability, particularly in
fairness contexts. Understanding how individual features influence model outcomes is crucial for building interpretable and equitable models. While feature importance metrics for accuracy are well-established, methods for assessing feature contributions to
fairness remain underexplored. We propose two model-agnostic approaches to measure fair feature importance. First, we propose to compare model
fairness before and after permuting feature values. This simple intervention-based approach decouples a feature and model predictions to measure its contribution to training. Second, we evaluate the
fairness of models trained with and without a given feature. This occlusion-based score enjoys dramatic computational simplification via minipatch learning. Our empirical results reflect the simplicity and effectiveness of our proposed metrics for multiple predictive tasks. Both methods offer simple, scalable, and interpretable solutions to quantify the influence of features on
fairness, providing new tools for responsible machine learning development.
Read the full abstract ▾
All authors Camille Little, Madeline Navarro, Santiago Segarra, Genevera Allen
Machine Learning
ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest
Jiacheng Li, Yixiong Meng, Yi wu et al. (+7 more)
Deep learning recommendation systems rely on feature interaction modules to model complex user-item relationships across sparse categorical and dense features. In large-scale ad ranking, increasing model capacity is a promising path to improving both predictive performance and business outcomes, yet production serving budgets impose strict constraints on latency and FLOPs. This creates a central tension: we want interaction modules that both scale effectively with additional compute and remain compute-efficient at serving time. In this work, we study how to scale feature interaction modules under a fixed serving budget. We find that naively scaling DCNv2 and MaskNet, despite their widespread adoption in industry, yields rapidly diminishing offline gains in the Pinterest ads ranking system. To overcome aforementioned limitations, we propose ML-DCN, an interaction module that integrates an instance-conditioned mask into a low-rank crossing layer, enabling per-example selection and amplification of salient interaction directions while maintaining efficient computation. This novel architecture combines the strengths of DCNv2 and MaskNet, scales efficiently with increased compute, and achieves state-of-the-art performance. Experiments on a large internal Pinterest ads
dataset show that ML-DCN achieves higher AUC than DCNv2, MaskNet, and recent scaling-oriented alternatives at matched FLOPs, and it scales more favorably overall as compute increases, exhibiting a stronger AUC-FLOPs trade-off. Finally, online A/B tests demonstrate statistically significant improvements in key ads metrics (including CTR and click-quality measures) and ML-DCN has been deployed in the production system with neutral serving cost.
Read the full abstract ▾
All authors Jiacheng Li, Yixiong Meng, Yi wu, Yun Zhao, Sharare Zehtabian, Jiayin Jin, Degao Peng, Jinfeng Zhuang, Qifei Shen, Kungang Li
Machine Learning
Gradient Residual Connections
Yangchen Pan, Qizhen Ying, Philip Torr et al. (+1 more)
Existing work has linked properties of a function's gradient to the difficulty of function approximation. Motivated by these insights, we study how gradient information can be leveraged to improve neural network's ability to approximate high-frequency functions, and we propose a gradient-based residual connection as a complement to the standard identity skip connection used in residual networks. We provide simple theoretical intuition for why gradient information can help distinguish inputs and improve the approximation of functions with rapidly varying behaviour. On a synthetic regression task with a high-frequency sinusoidal ground truth, we show that conventional residual connections struggle to capture high-frequency patterns. In contrast, our gradient residual substantially improves approximation quality. We then introduce a convex combination of the standard and gradient residuals, allowing the network to flexibly control how strongly it relies on gradient information. After validating the design choices of our proposed method through an ablation study, we further validate our approach's utility on the single-image super-resolution task, where the underlying function may be high-frequency. Finally, on standard tasks such as image classification and
segmentation, our method achieves performance comparable to standard residual networks, suggesting its broad utility.
Read the full abstract ▾
All authors Yangchen Pan, Qizhen Ying, Philip Torr, Bo Liu
Machine Learning · Cross-listed from cs.CR
One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning
Kotekar Annapoorna Prabhu, Andrew Gan and Zahra Ghodsi
Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the source of randomness. However, variations in design choices and implementations across different frameworks, software dependencies, and hardware backends along with the lack of statistical validation can lead to previously unexplored attack vectors on machine learning systems. Such attacks on randomness sources can be extremely covert, and have a history of exploitation in real-world systems. In this work, we examine the role of randomness in the machine learning development pipeline from an
adversarial point of view, and analyze the implementations of PRNGs in major machine learning frameworks. We present RNGGuard to help machine learning engineers secure their systems with low effort. RNGGuard statically analyzes a target library's source code and identifies instances of random functions and modules that use them. At runtime, RNGGuard enforces secure execution of random functions by replacing insecure function calls with RNGGuard's implementations that meet security specifications. Our evaluations show that RNGGuard presents a practical approach to close existing gaps in securing randomness sources in machine learning systems.
Read the full abstract ▾
Machine Learning
Weighted Wasserstein Barycenter of Gaussian Processes for exotic Bayesian Optimization tasks
Antonio Candelieri and Francesco Archetti
Exploiting the analogy between Gaussian Distributions and Gaussian Processes' posterior, we present how the weighted Wasserstein Barycenter of Gaussian Processes (W2BGP) can be used to unify, under a common framework, different exotic
Bayesian Optimization (BO) tasks. Specifically, collaborative/
federated BO, (synchronous) batch BO, and multi-fidelity BO are considered in this paper. Our empirical analysis proves that each one of these tasks requires just an appropriate weighting schema for the W2BGP, while the entire framework remains untouched. Moreover, we demonstrate that the most well-known BO acquisition functions can be easily re-interpreted under the proposed framework and also enable a more computationally efficient way to deal with the computation of the Wasserstein Barycenter, compared with state-of-the-art methods from the Machine Learning literature. Finally, research perspectives branching from the proposed approach are presented.
Read the full abstract ▾
Machine Learning
$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models
Ryozo Masukawa, Sanggeon Yun, Hyunwoo Oh et al. (+8 more)
Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized
language models (SLMs) can exhibit structured
reasoning without relying on large monolithic LLMs. We introduce soft hidden-state collaboration, where multiple heterogeneous frozen SLM experts are integrated through their internal representations via a trainable
attention interface. Experiments on
Reasoning Gym and GSM8K show that this latent integration is competitive with strong single-model RLVR baselines. Ablations further reveal a dual mechanism of expert utilization: for simpler arithmetic domains, performance gains can largely be explained by static expert preferences, whereas more challenging settings induce increasingly concentrated and structured expert
attention over training, indicating emergent specialization in how the router connects to relevant experts. Overall, hidden-state collaboration provides a compact mechanism for leveraging frozen experts, while offering an observational window into expert utilization patterns and their
evolution under RLVR.
Read the full abstract ▾
All authors Ryozo Masukawa, Sanggeon Yun, Hyunwoo Oh, SuhgHeon Jeong, Raheeb Hassa, Hanning Chen, Wenjun Huang, Mahdi Imani, Pietro Mercati, Nathaniel D. Bastian, Mohsen Imani
Machine Learning · Cross-listed from stat.ML
Quantifying Epistemic Uncertainty in Diffusion Models
Aditi Gupta, Raphael A. Meyer, Yotam Yaniv et al. (+2 more)
To ensure high quality outputs, it is important to quantify the epistemic uncertainty of
diffusion models. Existing methods are often unreliable because they mix epistemic and aleatoric uncertainty. We introduce a method based on Fisher information that explicitly isolates epistemic variance, producing more reliable plausibility scores for generated data. To make this approach scalable, we propose
FLARE (Fisher-Laplace Randomized
Estimator), which approximates the Fisher information using a uniformly random subset of model parameters. Empirically,
FLARE improves uncertainty estimation in synthetic time-series generation tasks, achieving more accurate and reliable filtering than other methods. Theoretically, we bound the convergence rate of our randomized approximation and provide analytic and empirical evidence that last-layer Laplace approximations are insufficient for this task.
Read the full abstract ▾
All authors Aditi Gupta, Raphael A. Meyer, Yotam Yaniv, Elynn Chen, N. Benjamin Erichson
Machine Learning
Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity
Jonathan Svirsky, Yehonathan Refael and Ofir Lindenbaum
Fully finetuning foundation
language models (LMs) with billions of parameters is often impractical due to high computational costs,
memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these challenges by adding small trainable modules to the frozen LM, they also increase
memory usage and do not reduce inference latency. We uncover an intriguing phenomenon: sparsifying specific model rows and columns enables efficient task adaptation without requiring weight tuning. We propose a scheme for effective finetuning via sparsification using training
stochastic gates, which requires minimal trainable parameters, reduces inference time, and removes 20–40% of model parameters without significant accuracy loss. Empirical results show it outperforms recent finetuning baselines in efficiency and performance. Additionally, we provide theoretical guarantees for the convergence of this
stochastic gating process, and show that our method admits a simpler and better-conditioned optimization landscape compared to LoRA. Our results highlight sparsity as a compelling mechanism for task-specific adaptation in LMs.
Read the full abstract ▾
Machine Learning
Faster Rates For Federated Variational Inequalities
Guanghui Wang and Satyen Kale
In this paper, we study
federated optimization for solving
stochastic variational inequalities (VIs), a problem that has attracted growing
attention in recent years. Despite substantial progress, a significant gap remains between existing convergence rates and the state-of-the-art bounds known for
federated convex optimization. In this work, we address this limitation by establishing a series of improved convergence rates. First, we show that, for general smooth and monotone variational inequalities, the classical Local Extra SGD
algorithm admits tighter guarantees under a refined analysis. Next, we identify an inherent limitation of Local Extra SGD, which can lead to excessive client drift. Motivated by this observation, we propose a new
algorithm, the Local Inexact Proximal Point
Algorithm with Extra Step (LIPPAX), and show that it mitigates client drift and achieves improved guarantees in several regimes, including bounded Hessian, bounded operator, and low-variance settings. Finally, we extend our results to
federated composite variational inequalities and establish improved convergence guarantees.
Read the full abstract ▾
Machine Learning
Boltzmann Reinforcement Learning for Noise resilience in Analog Ising Machines
Aditya Choudhary, Saaketh Desai and Prasad Iyer
Analog Ising machines (AIMs) have emerged as a promising paradigm for combinatorial optimization, utilizing physical dynamics to solve Ising problems with high energy efficiency. However, the performance of traditional optimization and sampling
algorithms on these platforms is often limited by inherent measurement noise. We introduce
BRAIN (Boltzmann Reinforcement for Analog Ising Networks), a distribution learning framework that utilizes variational reinforcement learning to approximate the Boltzmann distribution. By shifting from state-by-state sampling to aggregating information across multiple noisy measurements,
BRAIN is resilient to Gaussian noise characteristic of AIMs. We evaluate
BRAIN across diverse combinatorial
topologies, including the Curie-Weiss and 2D nearest-neighbor Ising systems. We find that under realistic 3% Gaussian measurement noise,
BRAIN maintains 98% ground state fidelity, whereas Markov Chain Monte Carlo (MCMC) methods degrade to 51% fidelity. Furthermore,
BRAIN reaches the MCMC-equivalent solution up to 192x faster under these conditions.
BRAIN exhibits $\mathcal{O}(N^{1.55})$ scaling up to 65,536
spins and maintains robustness against severe measurement uncertainty up to 40%. Beyond ground state optimization,
BRAIN accurately captures thermodynamic phase transitions and metastable states, providing a scalable and noise-resilient method for utilizing analog computing architectures in complex optimizations.
Read the full abstract ▾