MIMO-LP: A Multi-Input Multi-Output Framework for Subgraph-based Link Prediction

Link prediction (LP) is a fundamental problem in graph learning and can be broadly categorized into node-based and subgraph-based approaches. Compared to node-based approaches, subgraphbased LP methods often achieve superior predictive performance by exploiting localized structural information, but suffer from significant efficiency bottlenecks due to the high computational cost of per-query subgraph message passing operations. To this end, we propose MIMO-LP, a Multi-Input Multi-Output (MIMO) framework that accelerates subgraph-based LP via multiplexing. Given a batch of query node pairs and their corresponding subgraphs extracted from a shared full graph, MIMO-LP superposes their messagepassing processes into a shared latent space while ensuring minimal interference among them. This design enables MIMO-LP to multiplex multiple queries within a single forward pass during both training and inference, substantially reducing redundant message-passing computations in overlapping subgraph regions. Extensive experiments demonstrate that MIMO-LP achieves up to 44× speedup over existing one-to-one subgraph-based methods, while maintaining comparable predictive performance.