# Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling

arXiv: https://arxiv.org/abs/2212.03396 · HTML: https://mlsanity.com/paper/2212.03396/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- ["How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations](https://mlsanity.com/paper/1911.06473/) (2019)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification](https://mlsanity.com/paper/1503.01161/) (2015)
- [ECG Heartbeat Classification: A Deep Transferable Representation](https://mlsanity.com/paper/1805.00794/) (2018)
- [Interpretable and Steerable Sequence Learning via Prototypes](https://mlsanity.com/paper/1907.09728/) (2019)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers](https://mlsanity.com/paper/2103.12279/) (2021)
- [Why Attentions May Not Be Interpretable?](https://mlsanity.com/paper/2006.05656/) (2020)
- [Understanding Convolutional Neural Networks for Text Classification](https://mlsanity.com/paper/1809.08037/) (2018)
- [How Does Selective Mechanism Improve Self-Attention Networks?](https://mlsanity.com/paper/2005.00979/) (2020)

## Built on by (most cited first, 4 of 4)

- [Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction](https://mlsanity.com/paper/2401.01549/) (2024)
- [This looks like what? Challenges and Future Research Directions for Part-Prototype Models](https://mlsanity.com/paper/2502.09340/) (2025)
- [Advancing Interpretability in Text Classification through Prototype Learning](https://mlsanity.com/paper/2410.17546/) (2024)
- [Efficient User Sequence Learning for Online Services via Compressed Graph Neural Networks](https://mlsanity.com/paper/2406.02979/) (2024)

## Abstract (arXiv)

Prototype-based interpretability methods provide intuitive explanations of model prediction by comparing samples to a reference set of memorized exemplars or typical representatives in terms of similarity. In the field of sequential data modeling, similarity calculations of prototypes are usually based on encoded representation vectors. However, due to highly recursive functions, there is usually a non-negligible disparity between the prototype-based explanations and the original input. In this work, we propose a Self-Explaining Selective Model (SESM) that uses a linear combination of prototypical concepts to explain its own predictions. The model employs the idea of case-based reasoning by selecting sub-sequences of the input that mostly activate different concepts as prototypical parts, which users can compare to sub-sequences selected from different example inputs to understand model decisions. For better interpretability, we design multiple constraints including diversity, stability, and locality as training objectives. Extensive experiments in different domains demonstrate that our method exhibits promising interpretability and competitive accuracy.