Multi-Relational Learning at Scale with ADMM

Abstract: Learning from multiple-relational data which contains noise, ambiguities, or duplicate entities is essential to a wide range of applications such as statistical inference based on Web Linked Data, recommender systems, computational biology, and natural language processing. These tasks usually require working with very large and complex datasets - e.g., the Web graph - however, current approaches to multi-relational learning are not practical for such scenarios due to their high computational complexity and poor scalability on large data. In this paper, we propose a novel and scalable approach for multi-relational factorization based on consensus optimization. Our model, called ConsMRF, is based on the Alternating Direction Method of Multipliers (ADMM) framework, which enables us to optimize each target relation using a smaller set of parameters than the state-of-the-art competitors in this task. Due to ADMM's nature, ConsMRF can be easily parallelized which makes it suitable for large multi-relational data. Experiments on large Web datasets - derived from DBpedia, Wikipedia and YAGO - show the efficiency and performance improvement of ConsMRF over strong competitors. In addition, ConsMRF near-linear scalability indicates great potential to tackle Web-scale problem sizes.