Cross-Network Learning with Partially Aligned Graph Convolutional Networks

TL;DR

This paper introduces partially aligned graph convolutional networks that leverage shared nodes across multiple graphs to improve node representation learning for tasks like relation classification and link prediction.

Contribution

It proposes novel methods for cross-graph learning with partial node alignment, including model sharing, regularization, and alignment reconstruction, with theoretical analysis.

Findings

Superior performance on relation classification

Enhanced link prediction accuracy

Effective knowledge transfer across graphs

Abstract

Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data. Existing models were designed for the nodes on a single graph, which would not be able to utilize information across multiple graphs. The real world does have multiple graphs where the nodes are often partially aligned. For examples, knowledge graphs share a number of named entities though they may have different relation schema; collaboration networks on publications and awarded projects share some researcher nodes who are authors and investigators, respectively; people use multiple web services, shopping, tweeting, rating movies, and some may register the same email account across the platforms. In this paper, I propose partially aligned graph convolutional networks to learn node representations across the models. I investigate multiple methods (including model sharing, regularization, and alignment reconstruction) as well as theoretical analysis to positively transfer knowledge across the (small) set of partially aligned nodes. Extensive experiments on real-world knowledge graphs and collaboration networks show the superior performance of our proposed methods on relation classification and link prediction.