Bayram, Eda2021-10-192021-10-192021-10-19202210.1007/978-3-030-93409-5_14https://infoscience.epfl.ch/handle/20.500.14299/1822512110.08185Recent 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.multi-relational datalabel propagationnode regressiontext::conference output::conference proceedings::conference paper