Hypergraph-Based Dynamic Graph Node Classification

TL;DR

This paper introduces HYDG, a hypergraph-based model that captures multi-granularity dynamic graph features for improved node classification over time.

Contribution

It proposes a novel hypergraph-based framework that models both individual and group-level temporal dependencies in dynamic graphs.

Findings

HYDG outperforms existing methods on five real datasets.

Hypergraph modeling improves capturing diverse temporal dependencies.

Weighted information propagation enhances representation quality.

Abstract

Node classification on static graphs has achieved significant success, but achieving accurate node classification on dynamic graphs where node topology, attributes, and labels change over time has not been well addressed. Existing methods based on RNNs and self-attention only aggregate features of the same node across different time slices, which cannot adequately address and capture the diverse dynamic changes in dynamic graphs. Therefore, we propose a novel model named Hypergraph-Based Multi-granularity Dynamic Graph Node Classification (HYDG). After obtaining basic node representations for each slice through a GNN backbone, HYDG models the representations of each node in the dynamic graph through two modules. The individual-level hypergraph captures the spatio-temporal node representations between individual nodes, while the group-level hypergraph captures the multi-granularity group temporal representations among nodes of the same class. Each hyperedge captures different temporal dependencies of varying lengths by connecting multiple nodes within specific time ranges. More accurate representations are obtained through weighted information propagation and aggregation by the hypergraph neural network. Extensive experiments on five real dynamic graph datasets using two GNN backbones demonstrate the superiority of our proposed framework.