mlsanityData to 7 Oct 2026

Improving Interpretability via Explicit Word Interaction Graph Layer

arXiv 2302.02016 ↗First posted 3 Feb 2023cs.CL cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent NLP literature has seen growing interest in improving model interpretability. Along this direction, we propose a trainable neural network layer that learns a global interaction graph between words and then selects more informative words using the learned word interactions. Our layer, we call WIGRAPH, can plug into any neural network-based NLP text classifiers right after its word embedding layer. Across multiple SOTA NLP models and various NLP datasets, we demonstrate that adding the WIGRAPH layer substantially improves NLP models' interpretability and enhances models' prediction performance at the same time.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

35 of 48 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  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. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  8. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  9. 2015Variational Inference with Normalizing Flowscited by 2,161
  10. 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,471
  11. 2016Variational Inference: A Review for Statisticianscited by 1,466
  12. 2020Concept Bottleneck Modelscited by 1,022
23 more
  1. 2016Deep Variational Information Bottleneckcited by 915
  2. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  3. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  4. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  5. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
  6. 2017A simple neural network module for relational reasoningcited by 345
  7. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  8. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 279
  9. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  10. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  11. 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
  12. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  13. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  14. 2020Restricting the Flow: Information Bottlenecks for Attributioncited by 110
  15. 2018Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMscited by 67
  16. 2018Hierarchical interpretations for neural network predictionscited by 66
  17. 2020Generating Hierarchical Explanations on Text Classification via Feature Interaction Detectioncited by 57
  18. 2019Explaining a black-box using Deep Variational Information Bottleneck Approachcited by 35
  19. 2020Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifierscited by 35
  20. 2019Improving performance of deep learning models with axiomatic attribution priors and expected gradientscited by 32
  21. 2019Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretabilitycited by 22
  22. 2019On Attribution of Recurrent Neural Network Predictions via Additive Decompositioncited by 15
  23. 2019Improving the Explainability of Neural Sentiment Classifiers via Data Augmentationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 2.

6 papers.

  1. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  2. 2025Survey of Video Diffusion Models: Foundations, Implementations, and Applicationscited by 14
  3. 2024Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainabilitycited by 10
  4. 2024Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationalescited by 5
  5. 2023CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problemcited by 0
  6. 2024Empowering Prior to Court Legal Analysis: A Transparent and Accessible Dataset for Defensive Statement Classification and Interpretationcited by 0