mlsanityData to 7 Oct 2026

Relational Local Explanations

arXiv 2212.12374 ↗First posted 23 Dec 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The majority of existing post-hoc explanation approaches for machine learning models produce independent, per-variable feature attribution scores, ignoring a critical inherent characteristics of homogeneously structured data, such as visual or text data: there exist latent inter-variable relationships between features. In response, we develop a novel model-agnostic and permutation-based feature attribution approach based on the relational analysis between input variables. As a result, we are able to gain a broader insight into the predictions and decisions of machine learning models. Experimental evaluations of our framework in comparison with state-of-the-art attribution techniques on various setups involving both image and text data modalities demonstrate the effectiveness and validity of our method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

33 of 50 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  11. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  12. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
21 more
  1. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  2. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  3. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  4. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  5. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  6. 2020A Survey on Neural Network Interpretabilitycited by 291
  7. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  8. 2019Explainable Machine Learning in Deploymentcited by 210
  9. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  10. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  11. 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
  12. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 100
  13. 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
  14. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 86
  15. 2018Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMscited by 67
  16. 2018Hierarchical interpretations for neural network predictionscited by 66
  17. 2019Explainable AI for Trees: From Local Explanations to Global Understandingcited by 64
  18. 2020IROF: a low resource evaluation metric for explanation methodscited by 45
  19. 2020Why model why? Assessing the strengths and limitations of LIMEcited by 21
  20. 2020Jigsaw-VAE: Towards Balancing Features in Variational Autoencoderscited by 3
  21. 2021A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machinescited by 2

Built on by

Not cited yet.