# Interpretable and Steerable Sequence Learning via Prototypes

## TL;DR

ProSeNet is an interpretable deep sequence model that uses prototypes for predictions, enabling domain experts to refine models interactively while maintaining high accuracy across various applications.

## Contribution

The paper introduces ProSeNet, a novel prototype-based sequence learning model that combines interpretability, steerability, and competitive accuracy, with a new learning framework and prototype construction criteria.

## Key findings

- ProSeNet achieves accuracy comparable to state-of-the-art models.
- ProSeNet provides high-quality, human-aligned prototypes.
- Domain experts can refine prototypes interactively without performance loss.

## Abstract

One of the major challenges in machine learning nowadays is to provide predictions with not only high accuracy but also user-friendly explanations. Although in recent years we have witnessed increasingly popular use of deep neural networks for sequence modeling, it is still challenging to explain the rationales behind the model outputs, which is essential for building trust and supporting the domain experts to validate, critique and refine the model. We propose ProSeNet, an interpretable and steerable deep sequence model with natural explanations derived from case-based reasoning. The prediction is obtained by comparing the inputs to a few prototypes, which are exemplar cases in the problem domain. For better interpretability, we define several criteria for constructing the prototypes, including simplicity, diversity, and sparsity and propose the learning objective and the optimization procedure. ProSeNet also provides a user-friendly approach to model steering: domain experts without any knowledge on the underlying model or parameters can easily incorporate their intuition and experience by manually refining the prototypes. We conduct experiments on a wide range of real-world applications, including predictive diagnostics for automobiles, ECG, and protein sequence classification and sentiment analysis on texts. The result shows that ProSeNet can achieve accuracy on par with state-of-the-art deep learning models. We also evaluate the interpretability of the results with concrete case studies. Finally, through user study on Amazon Mechanical Turk (MTurk), we demonstrate that the model selects high-quality prototypes which align well with human knowledge and can be interactively refined for better interpretability without loss of performance.