Effective Decoding in Graph Auto-Encoder using Triadic Closure

TL;DR

This paper introduces a triad decoder for graph auto-encoders that considers interactions among three nodes simultaneously, improving link prediction, clustering, and graph generation by leveraging triadic closure.

Contribution

It proposes a novel triad decoder that incorporates triadic closure into graph auto-encoders, enhancing their ability to model complex local structures.

Findings

Improved accuracy in link prediction tasks.

Enhanced node clustering results.

Better preservation of graph characteristics.

Abstract

The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph convolutional network, the decoder reconstructs the graph structure by only considering two nodes at a time, thus ignoring possible interactions among edges. On the other hand, structured prediction, which considers the whole graph simultaneously, is computationally expensive. In this paper, we utilize the well-known triadic closure property which is exhibited in many real-world networks. We propose the triad decoder, which considers and predicts the three edges involved in a local triad together. The triad decoder can be readily used in any graph-based auto-encoder. In particular, we incorporate this to the (variational) graph auto-encoder. Experiments on link prediction, node clustering and graph generation show that the use of triads leads to more accurate prediction, clustering and better preservation of the graph characteristics.