ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
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.
Code (1)
Tasks
Knowledge Graph CompletionSimilar Papers 제목 키워드 기반
Revisiting the Message Passing in Heterophilous Graph Neural Networks
Graph Neural Networks (GNNs) have demonstrated strong performance in graph mining tasks due to their message-passing mechanism, which is aligned with the homophily assumption that adjacent nodes exhibit similar behaviors…
Graph MiningOn the under-reaching phenomenon in message-passing neural PDE solvers: revisiting the CFL condition
This paper proposes sharp lower bounds for the number of message passing iterations required in graph neural networks (GNNs) when solving partial differential equations (PDE). This significantly reduces the need for exha…
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing, and training reduces to dense per-node transformations. This desig…
CRoC: Context Refactoring Contrast for Graph Anomaly Detection with Limited Supervision
Graph Neural Networks (GNNs) are widely used as the engine for various graph-related tasks, with their effectiveness in analyzing graph-structured data. However, training robust GNNs often demands abundant labeled data, …
Graph Anomaly DetectionContrastive LearningGeneralised Coupled Tensor Factorisation
We derive algorithms for generalised tensor factorisation (GTF) by building upon the well-established theory of Generalised Linear Models. Our algorithms are general in the sense that we can compute arbitrary factorisati…