Chen, Yihong; Mishra, Pushkar; Franceschi, Luca; Minervini, Pasquale; Stenetorp, Pontus; Riedel, Sebastian; (2022) REFACTOR GNNS: Revisiting Factorisation-based Models from a Message-Passing Perspective. In: Koyejo, S and Mohamed, S and Agarwal, A and Belgrave, D and Cho, K and Oh, A, (eds.) Advances in Neural Information Processing Systems 35. (pp. pp. 1-13). Neural Information Processing Systems (NIPS)

Preview

PDF NeurIPS-2022-refactor-gnns-revisiting-factorisation-based-models-from-a-message-passing-perspective-Paper-Conference.pdf - Published Version Download (615kB) | Preview

Abstract

Factorisation-based Models (FMs), such as DistMult, have enjoyed enduring success for Knowledge Graph Completion (KGC) tasks, often outperforming Graph Neural Networks (GNNs). However, unlike GNNs, FMs struggle to incorporate node features and generalise to unseen nodes in inductive settings. Our work bridges the gap between FMs and GNNs by proposing REFACTOR GNNS. This new architecture draws upon both modelling paradigms, which previously were largely thought of as disjoint. Concretely, using a message-passing formalism, we show how FMs can be cast as GNNs by reformulating the gradient descent procedure as message-passing operations, which forms the basis of our REFACTOR GNNS. Across a multitude of well-established KGC benchmarks, our REFACTOR GNNS achieve comparable transductive performance to FMs, and state-of-the-art inductive performance while using an order of magnitude fewer parameters.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item