You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction
This addresses link prediction sparsity issues in domains like e-commerce or academic networks, but it is incremental as it builds on existing transfer learning methods by explicitly using intersection structure.
The paper tackles link prediction in sparse graphs by leveraging a complementary dense graph that shares nodes, proposing a Graph Intersection-induced Transfer Learning (GITL) framework that transfers knowledge from an intersection subgraph to the target graph, and shows it outperforms existing transfer learning baselines on e-commerce and citation datasets.
Link prediction is central to many real-world applications, but its performance may be hampered when the graph of interest is sparse. To alleviate issues caused by sparsity, we investigate a previously overlooked phenomenon: in many cases, a densely connected, complementary graph can be found for the original graph. The denser graph may share nodes with the original graph, which offers a natural bridge for transferring selective, meaningful knowledge. We identify this setting as Graph Intersection-induced Transfer Learning (GITL), which is motivated by practical applications in e-commerce or academic co-authorship predictions. We develop a framework to effectively leverage the structural prior in this setting. We first create an intersection subgraph using the shared nodes between the two graphs, then transfer knowledge from the source-enriched intersection subgraph to the full target graph. In the second step, we consider two approaches: a modified label propagation, and a multi-layer perceptron (MLP) model in a teacher-student regime. Experimental results on proprietary e-commerce datasets and open-source citation graphs show that the proposed workflow outperforms existing transfer learning baselines that do not explicitly utilize the intersection structure.