THeGCN: Temporal Heterophilic Graph Convolutional Network
This addresses a specific problem in graph learning for researchers and practitioners dealing with complex temporal and heterophilic graph data, representing an incremental advancement by combining existing techniques to handle a newly identified challenge.
The paper tackles the challenge of temporal edge heterophily in event-based continuous graphs, where edge heterophily and temporal heterophily co-exist, by proposing THeGCN, which uses low/high-pass graph signal filtering to capture both spatial and temporal heterophily, achieving state-of-the-art results on 5 real-world datasets.
Graph Neural Networks (GNNs) have exhibited remarkable efficacy in diverse graph learning tasks, particularly on static homophilic graphs. Recent attention has pivoted towards more intricate structures, encompassing (1) static heterophilic graphs encountering the edge heterophily issue in the spatial domain and (2) event-based continuous graphs in the temporal domain. State-of-the-art (SOTA) has been concurrently addressing these two lines of work but tends to overlook the presence of heterophily in the temporal domain, constituting the temporal heterophily issue. Furthermore, we highlight that the edge heterophily issue and the temporal heterophily issue often co-exist in event-based continuous graphs, giving rise to the temporal edge heterophily challenge. To tackle this challenge, this paper first introduces the temporal edge heterophily measurement. Subsequently, we propose the Temporal Heterophilic Graph Convolutional Network (THeGCN), an innovative model that incorporates the low/high-pass graph signal filtering technique to accurately capture both edge (spatial) heterophily and temporal heterophily. Specifically, the THeGCN model consists of two key components: a sampler and an aggregator. The sampler selects events relevant to a node at a given moment. Then, the aggregator executes message-passing, encoding temporal information, node attributes, and edge attributes into node embeddings. Extensive experiments conducted on 5 real-world datasets validate the efficacy of THeGCN.