Propagation on Multi-relational Graphs for Node Regression
It addresses the under-studied task of inferring continuous node features in multi-relational graphs, which is incremental as it builds on existing label propagation methods.
The paper tackles the problem of node regression on multi-relational graphs, proposing a novel propagation framework that extends label propagation to handle continuous features, and shows benefits in exploiting multi-relational structure across various scenarios.
Recent years have witnessed a rise in real-world data captured with rich structural information that can be conveniently depicted by multi-relational graphs. While inference of continuous node features across a simple graph is rather under-studied by the current relational learning research, we go one step further and focus on node regression problem on multi-relational graphs. We take inspiration from the well-known label propagation algorithm aiming at completing categorical features across a simple graph and propose a novel propagation framework for completing missing continuous features at the nodes of a multi-relational and directed graph. Our multi-relational propagation algorithm is composed of iterative neighborhood aggregations which originate from a relational local generative model. Our findings show the benefit of exploiting the multi-relational structure of the data in several node regression scenarios in different settings.