On the Generalization Capability of Temporal Graph Learning Algorithms: Theoretical Insights and a Simpler Method

arXiv:2402.16387v1 Announce Type: new
Abstract: Temporal Graph Learning (TGL) has become a prevalent technique across diverse real-world applications, especially in domains where data can be represented as a graph and evolves over time. Although TGL has recently seen notable progress in algorithmic solutions, its theoretical foundations remain largely unexplored. This paper aims at bridging this gap by investigating the generalization ability of different TGL algorithms (e.g., GNN-based, RNN-based, and memory-based methods) under the finite-wide over-parameterized regime. We establish the connection …

abstract algorithms applications arxiv become capability cs.ai cs.lg data diverse domains graph graph learning insights progress solutions temporal type world