An Information-Theoretic Analysis of Temporal GNNs
This work addresses a foundational gap for researchers in temporal graph learning, though it is incremental as it builds on existing information-theoretic frameworks.
The paper tackles the lack of formal analysis in Temporal Graph Neural Networks by using information theory, specifically adapting the information bottleneck concept and introducing a new Mutual Information Rate metric for temporal analysis.
Temporal Graph Neural Networks, a new and trending area of machine learning, suffers from a lack of formal analysis. In this paper, information theory is used as the primary tool to provide a framework for the analysis of temporal GNNs. For this reason, the concept of information bottleneck is used and adjusted to be suitable for a temporal analysis of such networks. To this end, a new definition for Mutual Information Rate is provided, and the potential use of this new metric in the analysis of temporal GNNs is studied.