Topology and Content Co-Alignment Graph Convolutional Learning

TL;DR

This paper introduces CoGL, a novel graph convolutional approach that aligns topology and content networks to improve node representation learning, especially when topology-content consistency is weak.

Contribution

The paper proposes a co-alignment method for GNNs that jointly optimizes topology and content networks, enhancing learning robustness against inconsistencies.

Findings

CoGL outperforms existing GNN models on six benchmarks.

The method effectively aligns topology and content networks.

Results show improved node classification accuracy.

Abstract

In traditional Graph Neural Networks (GNN), graph convolutional learning is carried out through topology-driven recursive node content aggregation for network representation learning. In reality, network topology and node content are not always consistent because of irrelevant or missing links between nodes. A pure topology-driven feature aggregation approach between unaligned neighborhoods deteriorates learning for nodes with poor structure-content consistency, and incorrect messages could propagate over the whole network as a result. In this paper, we advocate co-alignment graph convolutional learning (CoGL), by aligning the topology and content networks to maximize consistency. Our theme is to force the topology network to respect underlying content network while simultaneously optimizing the content network to respect the topology for optimized representation learning. Given a network, CoGL first reconstructs a content network from node features then co-aligns the content network and the original network though a unified optimization goal with (1) minimized content loss, (2) minimized classification loss, and (3) minimized adversarial loss. Experiments on six benchmarks demonstrate that CoGL significantly outperforms existing state-of-the-art GNN models.