mlsanityData to 7 Oct 2026

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective

arXiv 2207.09980 ↗First posted 20 Jul 2022cs.LG cs.AI cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

36 of 51 references.

References · 36

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  10. 2016Complex Embeddings for Simple Link Predictioncited by 897
  11. 2015Gated Graph Sequence Neural Networkscited by 792
  12. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
24 more
  1. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  2. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  3. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  4. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  5. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
  6. 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
  7. 2015Holographic Embeddings of Knowledge Graphscited by 181
  8. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  9. 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
  10. 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
  11. 2019Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphscited by 125
  12. 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
  13. 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
  14. 2019A Re-evaluation of Knowledge Graph Completion Methodscited by 73
  15. 2022Expressiveness and Approximation Properties of Graph Neural Networkscited by 63
  16. 2021How Powerful is Graph Convolution for Recommendation?cited by 50
  17. 2020L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networkscited by 48
  18. 2022Message passing all the way upcited by 47
  19. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  20. 2019Few-Shot Representation Learning for Out-Of-Vocabulary Wordscited by 30
  21. 2019Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoningcited by 23
  22. 2021How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence Viewcited by 17
  23. 2015Boolean Matrix Factorization and Noisy Completion via Message Passingcited by 12
  24. 2020Knowledge Base Completion: Baseline strikes back (Again)cited by 12

Built on by

Cited by year

Citing papers per year: 2023: 8; 2024: 3; 2025: 1.

12 papers.

  1. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  2. 2023Improving Language Plasticity via Pretraining with Active Forgettingcited by 43
  3. 2023A Multi-Task Perspective for Link Prediction with New Relation Types and Nodescited by 23
  4. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21
  5. 2023TouchUp-G: Improving Feature Representation through Graph-Centric Finetuningcited by 12
  6. 2024AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Predictioncited by 8
  7. 2023Inductive Knowledge Graph Completion with GNNs and Rules: An Analysiscited by 4
  8. 2023Temporal Smoothness Regularisers for Neural Link Predictorscited by 1
  9. 2023DURENDAL: Graph deep learning framework for temporal heterogeneous networkscited by 1
  10. 2024BloomGML: Graph Machine Learning through the Lens of Bilevel Optimizationcited by 1
  11. 2024Faithful Differentiable Reasoning with Reshuffled Region-based Embeddingscited by 1
  12. 2025iN2V: Bringing Transductive Node Embeddings to Inductive Graphscited by 0