mlsanityData to 14 Oct 2026

Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights

arXiv 2411.18343 ↗First posted 27 Nov 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized Federal learning(PFL) allows clients to cooperatively train a personalized model without disclosing their private dataset. However, PFL suffers from Non-IID, heterogeneous devices, lack of fairness, and unclear contribution which urgently need the interpretability of deep learning model to overcome these challenges. These challenges proposed new demands for interpretability. Low cost, privacy, and detailed information. There is no current interpretability method satisfying them. In this paper, we propose a novel interpretability method FreqX by introducing Signal Processing and Information Theory. Our experiments show that the explanation results of FreqX contain both attribution information and concept information. FreqX runs at least 10 times faster than the baselines which contain concept information.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 27 Nov 2024.

Builds on

36 of 51 references.

References · 36

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  10. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  11. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  12. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 547
24 more
  1. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  2. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  3. 2021Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depthcited by 419
  4. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  5. 2019Full-Gradient Representation for Neural Network Visualizationcited by 191
  6. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 178
  7. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  8. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 159
  9. 2020Debugging Tests for Model Explanationscited by 147
  10. 2022Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practicecited by 136
  11. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  12. 2022Impossibility Theorems for Feature Attributioncited by 78
  13. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
  14. 2020IROF: a low resource evaluation metric for explanation methodscited by 46
  15. 2021Order in the Court: Explainable AI Methods Prone to Disagreementcited by 36
  16. 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
  17. 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attributioncited by 21
  18. 2022Attribution-based Explanations that Provide Recourse Cannot be Robustcited by 20
  19. 2023On the Robustness of Removal-Based Feature Attributionscited by 19
  20. 2024Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learningcited by 9
  21. 2023Learning Time-Invariant Representations for Individual Neurons from Population Dynamicscited by 8
  22. 2023Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detectioncited by 6
  23. 2024Provably Better Explanations with Optimized Aggregation of Feature Attributionscited by 6
  24. 2021Frequency Principle in Deep Learning Beyond Gradient-descent-based Trainingcited by 4

Built on by

Not cited yet.