mlsanityData to 14 Oct 2026

Feature Attribution in Directed Acyclic Graphs Using Edge Intervention

arXiv 2606.15273 ↗First posted 13 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal relationships, even when a causal structure is provided. Existing methods typically adopt a node-centric view, attributing importance solely to individual features. Consequently, they often fail to simultaneously capture the externality and exogenous influence of features, leading to unreasonable interpretations. To overcome these limitations, we propose a novel feature attribution method called DAG-SHAP, which is based on edge intervention. DAG-SHAP treats each feature edge as an individual attribution object, ensuring that both externality and exogenous contributions of features are appropriately captured. Additionally, we introduce an approximation method for efficiently computing DAG-SHAP. Extensive experiments on both real and synthetic datasets validate the effectiveness of DAG-SHAP. Our code is available at https://github.com/ZJU-DIVER/DAG-SHAP.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 13 Jun 2026.

Builds on

23 of 45 references.

References · 23

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  7. 2019The many Shapley values for model explanationcited by 344
  8. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  9. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 148
  10. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  11. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  12. 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
11 more
  1. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  2. 2021Explaining a Series of Models by Propagating Shapley Valuescited by 37
  3. 2024Causal Concept Graph Models: Beyond Causal Opacity in Deep Learningcited by 29
  4. 2021Counterfactual Shapley Additive Explanationscited by 22
  5. 2020Quantifying intrinsic causal contributions via structure preserving interventionscited by 12
  6. 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanationcited by 6
  7. 2025Practical do-Shapley Explanations with Estimand-Agnostic Causal Inferencecited by 6
  8. 2023PWSHAP: A Path-Wise Explanation Model for Targeted Variablescited by 3
  9. 2024One Wave To Explain Them All: A Unifying Perspective On Feature Attributioncited by 3
  10. 2020Marginal Contribution Feature Importance -- an Axiomatic Approach for The Natural Casecited by 2
  11. 2024Prospector Heads: Generalized Feature Attribution for Large Models & Datacited by 1

Built on by

Not cited yet.