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.
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.
Related stories
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 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...
arXiv Machine Learning
Aug 11
General OOD Detection via Model-aware and Subspace-aware Variable Priority
arXiv:2512. 13003v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is essential for determining when a supervised model encounters inputs that differ meaningfully from its training distribution.
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.
arXiv Machine Learning
Sep 18
Evaluating Explanation Methods by the Predictors They Induce
The paper proposes a new evaluation test for explanation methods: if an explanation accurately captures how a model uses its features, one should be able to reconstruct the model’s predictions from it. The authors convert explanations into predictors by summing feature effects and assess how well these predictors reproduce the model on unseen data, without any fitting. They apply this test to partial dependence plots, accumulated local effects, SHAP, and LIME across multiple datasets and model families, showing that the best method depends on feature dependence and that some existing quality metrics can favor flawed explanations.
arXiv Machine Learning
Sep 10
Learn to Rank: Visual Attribution by Learning Importance Ranking
arXiv:2604.05819v2 Announce Type: replace-cross Abstract: Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical...
arXiv Computer Vision
Sep 7
The Neglected Baseline in Model Interpretation
The paper highlights that many current model interpretation techniques overlook the baseline, leading to inaccurate or incorrect explanations. It redefines the interpretation task, unifies gradient-based, Integrated Gradients, and Taylor expansion methods, and explicitly identifies appropriate baselines for each. The authors critique existing methods, propose a new interpretation approach with a clear baseline, and demonstrate its improved performance across layers.
arXiv Machine Learning
Jul 15
Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints for Reliable Decision-Making
arXiv:2602. 07008v3 Announce Type: replace-cross Abstract: Reliable models should not only predict correctly, but also justify decisions with acceptable evidence.
arXiv AI
Jun 9
SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions
arXiv:2606. 07590v1 Announce Type: cross Abstract: Pathology foundation models are pretrained on large streams of WSI-derived patches, while supervision during data construction is often slide-level, sparse, or heterogeneous.
arXiv AI
Jul 7
EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs
arXiv:2512. 22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biological findings.
Hugging Face Trending Papers
Aug 16
Scalable Black-Box Model Attribution for Images
The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? Existing methods have grown as elaborate as the genera...