GINTRIP: Interpretable Temporal Graph Regression using Information bottleneck and Prototype-based method

TL;DR

This paper presents GINTRIP, a novel framework combining Information Bottleneck and prototype-based methods to improve interpretability in temporal graph regression, demonstrating superior accuracy and explainability on real-world datasets.

Contribution

Introduces the first combined IB and prototype-based approach for interpretable temporal GNNs, with a new MI bound and multi-task learning for enhanced interpretability.

Findings

Outperforms existing methods in forecasting accuracy.

Achieves higher interpretability metrics like fidelity.

Effective on real-world traffic and crime datasets.

Abstract

Deep neural networks (DNNs) have demonstrated remarkable performance across various domains, but their inherent complexity makes them challenging to interpret. This is especially true for temporal graph regression tasks due to the complex underlying spatio-temporal patterns in the graph. While interpretability concerns in Graph Neural Networks (GNNs) mirror those of DNNs, no notable work has addressed the interpretability of temporal GNNs to the best of our knowledge. Innovative methods, such as prototypes, aim to make DNN models more interpretable. However, a combined approach based on prototype-based methods and Information Bottleneck (IB) principles has not yet been developed for temporal GNNs. Our research introduces a novel approach that uniquely integrates these techniques to enhance the interpretability of temporal graph regression models. The key contributions of our work are threefold: We introduce the Graph INterpretability in Temporal Regression task using Information bottleneck and Prototype (GINTRIP) framework, the first combined application of IB and prototype-based methods for interpretable temporal graph tasks. We derive a novel theoretical bound on mutual information (MI), extending the applicability of IB principles to graph regression tasks. We incorporate an unsupervised auxiliary classification head, fostering diverse concept representation using multi-task learning, which enhances the model's interpretability. Our model is evaluated on real-world datasets like traffic and crime, outperforming existing methods in both forecasting accuracy and interpretability-related metrics such as MAE, RMSE, MAPE, and fidelity.