mlsanityData to 7 Oct 2026

Improving Attribution Methods by Learning Submodular Functions

arXiv 2104.09073 ↗First posted 19 Apr 2021cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are natural for attribution as they are known to accurately model the principle of diminishing returns. A new formulation for learning a deep submodular set function that is consistent with the real-valued attribution maps obtained by existing attribution methods is proposed. The final attribution value of a feature is then defined as the marginal gain in the induced submodular score of the feature in the context of other highly attributed features, thus decreasing the attribution of redundant yet discriminatory features. Experiments on multiple datasets illustrate that the proposed attribution method achieves higher specificity along with good discriminative power. The implementation of our method is publicly available at https://github.com/Piyushi-0/SEA-NN.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

37 of 56 references.

References · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  11. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  12. 2014Striving for Simplicity: The All Convolutional Netcited by 983
25 more
  1. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  2. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  3. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  4. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  5. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  6. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  7. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  8. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 403
  9. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  10. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  11. 2017Interpretable Convolutional Neural Networkscited by 161
  12. 2016Grad-CAM: Why did you say that?cited by 159
  13. 2019XRAI: Better Attributions Through Regionscited by 116
  14. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  15. 2019Neural Network Attributions: A Causal Perspectivecited by 77
  16. 2020How does this interaction affect me? Interpretable attribution for feature interactionscited by 73
  17. 2019Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networkscited by 49
  18. 2020Smoothed Geometry for Robust Attributioncited by 38
  19. 2020A simple defense against adversarial attacks on heatmap explanationscited by 23
  20. 2019Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretationcited by 22
  21. 2018A Human-Grounded Evaluation Benchmark for Local Explanations of Machine Learningcited by 21
  22. 2020Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attributioncited by 19
  23. 2020DANCE: Enhancing saliency maps using decoyscited by 10
  24. 2017Streaming Weak Submodularity: Interpreting Neural Networks on the Flycited by 9
  25. 2020Concave Aspects of Submodular Functionscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 0; 2025: 1.

5 papers.

  1. 2022Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selectioncited by 6
  2. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  3. 2025Advances in Set Function Learning: A Survey of Techniques and Applicationscited by 3
  4. 2022Provable Robust Saliency-based Explanationscited by 1
  5. 2023Robust Ranking Explanationscited by 0