Graph Representation Learning via Contrastive Predictive Coding

Abstract

Graph representation learning has emerged as a crucial technique in various domains, including social network analysis, drug discovery, and recommendation systems. However, many existing methods struggle to effectively capture long-range dependencies within graphs, leading to suboptimal representations. This paper introduces a novel approach to graph representation learning based on Contrastive Predictive Coding (CPC). We leverage the inherent predictive structure of graphs by training models to predict future nodes based on their contextual information. This allows us to learn representations that are sensitive to long-range relationships. Our method, CPC-Graph, utilizes a recurrent neural network to encode the graph structure and predict future nodes, minimizing the difference between predicted and actual representations. We demonstrate the effectiveness of CPC-Graph through theoretical analysis and the formulation of key equations, showcasing its ability to capture dependencies efficiently. The core claim of this work is that existing graph representation learning methods often struggle to capture long-range dependencies. This new method employs Contrastive Predictive Coding (CPC) to address this issue, providing a robust solution for learning graph representations.