A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes
This work addresses a domain-specific problem in relational learning for graph-based AI, offering an incremental improvement over prior methods.
The paper tackles the challenge of inductive link prediction in attributed multigraphs with novel nodes and relation types, extending double equivariance to multi-task double equivariance to handle distinct predictive patterns across relation types, and demonstrates effective generalization on real-world datasets.
The task of inductive link prediction in (discrete) attributed multigraphs infers missing attributed links (relations) between nodes in new test multigraphs. Traditional relational learning methods face the challenge of limited generalization to test multigraphs containing both novel nodes and novel relation types not seen in training. Recently, under the only assumption that all relation types share the same structural predictive patterns (single task), Gao et al. (2023) proposed a link prediction method using the theoretical concept of double equivariance (equivariance for nodes & relation types), in contrast to the (single) equivariance (only for nodes) used to design Graph Neural Networks (GNNs). In this work we further extend the double equivariance concept to multi-task double equivariance, where we define link prediction in attributed multigraphs that can have distinct and potentially conflicting predictive patterns for different sets of relation types (multiple tasks). Our empirical results on real-world datasets demonstrate that our approach can effectively generalize to test graphs with multi-task structures without access to additional information.