mlsanityData to 7 Oct 2026

Negative Flux Aggregation to Estimate Feature Attributions

arXiv 2301.06989 ↗First posted 17 Jan 2023cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

There are increasing demands for understanding deep neural networks' (DNNs) behavior spurred by growing security and/or transparency concerns. Due to multi-layer nonlinearity of the deep neural network architectures, explaining DNN predictions still remains as an open problem, preventing us from gaining a deeper understanding of the mechanisms. To enhance the explainability of DNNs, we estimate the input feature's attributions to the prediction task using divergence and flux. Inspired by the divergence theorem in vector analysis, we develop a novel Negative Flux Aggregation (NeFLAG) formulation and an efficient approximation algorithm to estimate attribution map. Unlike the previous techniques, ours doesn't rely on fitting a surrogate model nor need any path integration of gradients. Both qualitative and quantitative experiments demonstrate a superior performance of NeFLAG in generating more faithful attribution maps than the competing methods. Our code is available at urlhttps://github.com/xinli0928/NeFLAG

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 17 Jan 2023.

Builds on

22 of 35 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  10. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  11. 2020Transformer Interpretability Beyond Attention Visualizationcited by 620
  12. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
10 more
  1. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 248
  2. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  3. 2019XRAI: Better Attributions Through Regionscited by 116
  4. 2021Guided Integrated Gradients: An Adaptive Path Method for Removing Noisecited by 102
  5. 2021Do Input Gradients Highlight Discriminative Features?cited by 52
  6. 2021Explaining a Series of Models by Propagating Shapley Valuescited by 37
  7. 2021Fast Axiomatic Attribution for Neural Networkscited by 35
  8. 2020Investigating Saturation Effects in Integrated Gradientscited by 22
  9. 2020Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraintscited by 10
  10. 2020Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainabilitycited by 9

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4; 2025: 1.

7 papers.

  1. 2024Gradient based Feature Attribution in Explainable AI: A Technical Reviewcited by 34
  2. 2024Facial Affective Behavior Analysis with Instruction Tuningcited by 26
  3. 2023Interpretability-Aware Vision Transformercited by 8
  4. 2023Fairness-aware Vision Transformer via Debiased Self-Attentioncited by 6
  5. 2024QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanationscited by 4
  6. 2025Enhancing Interpretability for Vision Models via Shapley Value Optimizationcited by 2
  7. 2024Fast Explanations via Policy Gradient-Optimized Explainercited by 1