THeGCN: Temporal Heterophilic Graph Convolutional Network

2024-12-21

AI Summary

Modeling event-driven continuous-time graphs is challenging due to the coexistence of spatial and temporal heterogeneity. Method: This paper introduces, for the first time, the concept of *temporal edge heterogeneity* and establishes a unified modeling framework: (1) it proposes a novel metric to quantify temporal edge heterogeneity; (2) it incorporates a dual-path low-pass/high-pass graph signal filtering mechanism to jointly address spatiotemporal heterogeneity; and (3) it decouples event-level temporal sampling from joint message passing over multi-attribute features (nodes, edges, and timestamps), enabling fine-grained modeling of temporal dependencies. Results: Evaluated on five real-world datasets, the model achieves an average accuracy improvement of 3.2% over state-of-the-art methods, demonstrating the effectiveness and generalizability of the proposed spatiotemporal joint modeling paradigm.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

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.

Problem

• Temporal Heterogeneity
• Complex Network Analysis
• Event Graph Processing

Innovation

• Time-Varying Networks
• Graph Neural Networks
• Temporal Heterogeneity