Feature Attribution

Ask about this topic

Overview

Feature attribution studies how to assign responsibility for a model’s prediction to parts of its input, such as image regions, text tokens, time-series measurements, or graph features. Common approaches include gradients and relevance propagation, perturbation and masking, Shapley values, and counterfactual or causal interventions; some methods instead build explanations into the model. Researchers evaluate explanations for faithfulness, stability, sparsity, localization, and usefulness across tasks such as image classification, language modeling, medical prediction, and time-series forecasting. A central challenge is that attributions can change with the model architecture, baseline, perturbation choices, or correlations among features, so no single method or metric is reliable in every setting.

Latest papers

CardsList

234 papers20 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

  1. How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional features

    Mar 5, 2026Mark A. van de Wiel, Jeroen Goedhart, Martin Jullum +1Feature AttributionShapley Value Attribution

    Dept of Epidemiology and Data Science, Amsterdam Public Health research institute, Amsterdam University Medical Centers, Amsterdam, The Netherlands · Norwegian Computing Center, Oslo, Norway

  2. From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

    Mar 5, 2026Cenwei Zhang, Lin Zhu, Manxi Lin +1Feature AttributionShapley Value Attribution

    Aalto University, Espoo, Finland · Alibaba, Hangzhou, China · Technical University of Denmark, Copenhagen, Denmark

  3. Missingness Bias Calibration in Feature Attribution Explanations

    Mar 5, 2026Shailesh Sridhar, Anton Xue, Eric WongFeature AttributionPerturbation-Based Feature Attribution

    University of Pennsylvania · University of Texas at Austin

  4. Feature-level Interaction Explanations in Multimodal Transformers

    Mar 4, 2026Yeji Kim, Housam Khalifa Bashier Babiker, Mi-Young Kim +1Multimodal UnderstandingFeature Attribution

    University of Alberta, Edmonton, AB, Canada · University of Waikato, Hamilton, New Zealand · University of Alberta, Camrose, AB, Canada

  5. Exact Functional ANOVA Decomposition for Categorical Inputs Models

    Mar 3, 2026Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa +2Feature AttributionShapley Value Attribution

    IMT, SINCLAIR AI Lab · EDF R&D, SINCLAIR Lab · Université de Toulouse +6

  6. What Helps---and What Hurts: Bidirectional Explanations for Vision Transformers

    Mar 2, 2026Qin Su, Tie LuoTransformer InterpretabilityExplainable Image Classification

    Department of Electrical and Computer Engineering University of Kentucky, Lexington, KY, USA

  7. AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

    Mar 1, 2026Pengfei Zhang, Tianxin Xie, Minghao Yang +1Flow-Based Generative ModelingFlow Matching

    AI Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou).

  8. A Polynomial-Time Axiomatic Alternative to SHAP for Feature Attribution

    Feb 28, 2026Kazuhiro Hiraki, Shinichi Ishihara, Takumi Kongo +1Feature AttributionShapley Value Attribution

    International Monetary Fund · Independent Researcher · Fukuoka University +1

  9. What You Read is What You Classify: Highlighting Attributions to Text and Text-Like Inputs

    Feb 27, 2026Daniel S. Berman, Brian Merritt, Stanley Ta +4Explainable Text ClassificationExplainable Artificial Intelligence

    Johns Hopkins Applied Physics Laboratory, 11100 Johns Hopkins Rd., Laurel, MD 20723, USA. · Current affiliation: Google DeepMind, 14–18 Handyside Street, London, N1C 4DN, United Kingdom

  10. Fair feature attribution for multi-output prediction: a Shapley-based perspective

    Feb 26, 2026Umberto Biccari, Alain Ibáñez de Opakua, José María Mato +3Feature AttributionShapley Value Attribution

  11. cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context

    Feb 23, 2026Jörg Martin, Stefan HaufeFeature AttributionShapley Value Attribution

    Physikalisch-Technische Bundesanstalt, Berlin, Germany · Technische Universität Berlin, Berlin, Germany · Charité – Universitätsmedizin Berlin, Berlin, Germany

  12. DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

    Feb 22, 2026Krishna Khadka, Yu Lei, Raghu N. Kacker +1Explainable Image ClassificationFeature Attribution

    Department of Computer Science & Engineering The University of Texas at Arlington Arlington, Texas, USA · Information Technology Laboratory National Institute of Standards and Technology (NIST) Gaithersburg, Maryland, USA

  13. Owen-based Semantics and Hierarchy-Aware Explanation (O-Shap)

    Feb 19, 2026Xiangyu Zhou, Chenhan Xiao, Yang WengFeature AttributionSHAP Feature Attribution

    Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, Arizona, United States

  14. Functional Decomposition and Shapley Interactions for Interpreting Survival Models

    Feb 18, 2026Sophie Hanna Langbein, Hubert Baniecki, Fabian Fumagalli +3Feature AttributionFeature Interaction Modeling

    Leibniz Institute for Prevention Research and Epidemiology – BIPS · Faculty of Mathematics and Computer Science, University of Bremen · University of Warsaw +3

  15. Explanation Multiplicity in SHAP: Characterization and Assessment

    Jan 19, 2026Hyunseung Hwang, Seungeun Lee, Lucas Rosenblatt +2SHAP Feature AttributionFeature Attribution

    KAIST, Daejeon, Republic of Korea · New York University, New York, NY, USA

  16. Motion Attribution for Video Generation

    Jan 13, 2026Xindi Wu, Despoina Paschalidou, Jun Gao +5Gradient-Based AttributionFeature Attribution

    NVIDIA · Princeton University · University of Michigan +3

  17. Explainability of Complex AI Models with Correlation Impact Ratio

    Jan 10, 2026Poushali Sengupta, Rabindra Khadka, Sabita Maharjan +5Feature AttributionInterpretable ML

    Institute of Informatics, University of Oslo, Oslo, Norway · Department of Computer Science, Oslo Metropolitan University, Oslo, Norway · Aalborg University, Denmark

  18. CID: Measuring Feature Importance Through Counterfactual Distributions

    Nov 19, 2025Eddie Conti, Álvaro Parafita, Axel BrandoFeature AttributionExplainability Evaluation

    TAIES Group, HPES Lab, Barcelona Supercomputing Center (BSC)

  19. Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)

    Oct 26, 2025Sze Chai Leung, Di Zhou, H. Jane BaeFeature Attribution

    Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, CA 91125, USA. · Lynn Booth & Kent Kresa Department of Aerospace, California Institute of Technology, Pasadena, CA 91125, USA. · Department of Mechanical and Aerospace Engineering, University of Tennessee, Knoxville, TN 37996, USA.

  20. Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

    Sep 26, 2025Jiawei Liang, Jianjie Huang, Ruoyu Chen +4Feature AttributionMultimodal Large Language Models

    Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, China · Zhongguan-cun Academy, Beijing 100094, China · University of Chinese Academy of Sciences, Beijing 100049, China +2

  21. Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability

    Sep 25, 2025Ali Yavari, Alireza Mohamadi, Elham Beydaghi +2Feature AttributionPerturbation-Based Feature Attribution

    Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria · Independent · Dept. of Computer Engineering, Sharif University of Technology, Tehran, Iran +1

  22. Explainable embeddings with Distance Explainer

    May 21, 2025Christiaan Meijer, E. G. Patrick BosFeature AttributionPerturbation-Based Feature Attribution

    Netherlands eScience Center, Science Park 402, 1098 XH Amsterdam, Netherlands · Center for Information Technology, University of Groningen, P.O. Box 11044, 9700 CA Groningen, Netherlands

  23. Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection

    Apr 1, 2025Ruoyu Chen, Siyuan Liang, Jingzhi Li +4Feature AttributionVLM Interpretability

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China · University of Chinese Academy of Sciences, Beijing 100049, China · College of Computing and Data Science, Nanyang Technological University, 639798, Singapore +4

  24. CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions

    Jun 17, 2024Ge Shi, Fangyi Liu, Ziwen Kan +1Gradient-Based AttributionFeature Attribution

    Department of Computer Science University of California, Davis