IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphs

TL;DR

This paper introduces IMPaCT, a novel method for domain adaptation in temporal graphs that improves semi-supervised node classification by imposing invariance based on temporal structure, supported by theoretical analysis and experiments.

Contribution

The paper proposes IMPaCT, a new approach that explicitly accounts for temporal graph properties to enhance domain adaptation, along with the TSBM for testing general GNNs.

Findings

IMPaCT outperforms SOTA by 3.8% on ogbn-mag.

IMPaCT incorporates invariance principles tailored for chronological splits.

Theoretical upper bound on generalization error is derived.

Abstract

This paper addresses domain adaptation challenges in graph data resulting from chronological splits. In a transductive graph learning setting, where each node is associated with a timestamp, we focus on the task of Semi-Supervised Node Classification (SSNC), aiming to classify recent nodes using labels of past nodes. Temporal dependencies in node connections create domain shifts, causing significant performance degradation when applying models trained on historical data into recent data. Given the practical relevance of this scenario, addressing domain adaptation in chronological split data is crucial, yet underexplored. We propose Imposing invariance with Message Passing in Chronological split Temporal Graphs (IMPaCT), a method that imposes invariant properties based on realistic assumptions derived from temporal graph structures. Unlike traditional domain adaptation approaches which rely on unverifiable assumptions, IMPaCT explicitly accounts for the characteristics of chronological splits. The IMPaCT is further supported by rigorous mathematical analysis, including a derivation of an upper bound of the generalization error. Experimentally, IMPaCT achieves a 3.8% performance improvement over current SOTA method on the ogbn-mag graph dataset. Additionally, we introduce the Temporal Stochastic Block Model (TSBM), which replicates temporal graphs under varying conditions, demonstrating the applicability of our methods to general spatial GNNs.