# Improving Interpretability via Explicit Word Interaction Graph Layer

arXiv: https://arxiv.org/abs/2302.02016 · HTML: https://mlsanity.com/paper/2302.02016/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 48 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 30 of 35)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs](https://mlsanity.com/paper/1801.05453/) (2018)
- [Hierarchical interpretations for neural network predictions](https://mlsanity.com/paper/1806.05337/) (2018)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [Explaining a black-box using Deep Variational Information Bottleneck Approach](https://mlsanity.com/paper/1902.06918/) (2019)

## Built on by (most cited first, 6 of 6)

- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Survey of Video Diffusion Models: Foundations, Implementations, and Applications](https://mlsanity.com/paper/2504.16081/) (2025)
- [Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability](https://mlsanity.com/paper/2408.08137/) (2024)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem](https://mlsanity.com/paper/2312.08157/) (2023)
- [Empowering Prior to Court Legal Analysis: A Transparent and Accessible Dataset for Defensive Statement Classification and Interpretation](https://mlsanity.com/paper/2405.10702/) (2024)

## 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.