arXiv Machine Learning
Jun 3
Attribution via Distributional Paths for Information Revelation
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
On Pitfalls of $\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective
arXiv:2304. 13836v5 Announce Type: replace-cross Abstract: The RemOve-And-Retrain (ROAR) benchmark is widely used to evaluate feature attribution methods, yet its validity remains underexplored from an information-theoretic perspective.
Related stories
arXiv Machine Learning
Jun 10
XtrAIn: Training-Guided Occlusion for Feature Attribution
arXiv:2606. 10877v1 Announce Type: new Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output.
arXiv Machine Learning
Jun 16
Enhancing Visual Feature Attribution via Weighted Integrated Gradients
arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.
arXiv AI
Jul 23
In-Run Data Shapley for Adam Optimizer
arXiv:2602. 00329v4 Announce Type: replace-cross Abstract: Reliable data attribution is essential for mitigating bias and reducing computational waste in modern machine learning, with the Shapley value serving as the theoretical gold standard.
arXiv Machine Learning
Sep 21
Data Attribution via Sketched Metadifferentiation
The paper introduces two algorithms, MAGE and SPELL, that enable efficient data attribution in neural networks by estimating a large influence matrix from a limited number of measurements. These methods leverage existing metagradient techniques without additional computational overhead, addressing the challenge of predicting the impact of removing training data in non‑convex models. Experiments show that MAGE and SPELL outperform current baselines across various training scales and measurement budgets.
arXiv AI
Sep 16
ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers
The paper introduces ResLRP, an extension of Layer-wise Relevance Propagation that explicitly handles residual connections in Vision Transformers to prevent attribution explosion. It demonstrates that residual cancellation causes instability in ViT explanations, and that ResLRP improves faithfulness and localization across a wide range of ViT architectures, including Vision Language Models. The method also provides a diagnostic measure for predicting attribution degradation and successfully localizes Sparse Autoencoder features.
Hugging Face Trending Papers
Jul 30
Scaling Vision-Language Models Is Not Enough to Mitigate Bias
Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present the first large-scale empirical study of 194 publicly available VLMs, including 16 model families, covering a wide range of model sizes, 24 training datasets, and three evaluation benchmarks, namely ImageNet (overall performance), CelebA (typical single-attribute bias), and UrbanCars (complex multi-attribute biases).
arXiv AI
Jun 10
Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification
arXiv:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.
arXiv Machine Learning
Jun 2
SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
arXiv:2601. 22276v2 Announce Type: replace Abstract: As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces.
arXiv Machine Learning
Sep 15
Data Attribution at Scale via Influence Matrix Estimation
Data Attribution at Scale via Influence Matrix Estimation proposes a scalable approach to quantify how individual training examples influence a model’s predictions. The authors introduce two algorithms, MAGE and SPELL, that reconstruct an influence matrix from a limited number of measurements without extra computational cost, improving over existing baselines across various training scales and budgets.
arXiv AI
Jun 2
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
arXiv:2601. 22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output.
arXiv Computer Vision
Aug 25
Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints
arXiv:2602.07008v5 Announce Type: replace Abstract: Reliable models should not only predict correctly, but also base their decisions on acceptable evidence. However, conventional supervised learning...