Research map / Graph learning / GNN architectures
ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
Yihong Chen, Pushkar Mishra, Luca Franceschi, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ReFactor GNN encoder instead of lookup table (FM) | DistMult decoder · UMLS | test MRR: 0.90 -> 0.93 | Improved |
| use ReFactor GNN encoder instead of lookup table (FM) | DistMult decoder · CoDEx-S | test MRR: 0.43 -> 0.44 | No clear effect |
| use ReFactor GNN encoder instead of lookup table (FM) | DistMult decoder · FB15K237 | test MRR: 0.30 -> 0.33 | Improved |
| use ReFactor GNNs instead of GraIL, random node features | ReFactor GNNs · FB15K237_v1 inductive | test MRR: +23% | Improved |
| use ReFactor GNNs instead of GraIL, textual node features | ReFactor GNNs · FB15K237_v1 inductive | test MRR: +43% | Improved |
| use ReFactor GNNs instead of NBFNet, textual node features | ReFactor GNNs · FB15K237_v1 inductive | test MRR: +10% | Improved |
| increase message-passing layers from 1 to 3, 6, 9 | ReFactor GNNs · FB15K237_v1 inductive | test MRR | Improved |
| increase message-passing layers to 6 and 9 | GAT · FB15K237_v1 inductive | test MRR | Hurt |
Closest papers by meaning
- On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning (NeurIPS 2025 · similarity 0.89)
- Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (ICML 2025 · similarity 0.88)
- Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks (ICLR 2024 · similarity 0.88)
- Towards Bridging Generalization and Expressivity of Graph Neural Networks (ICLR 2025 · similarity 0.88)
- Recurrent Graph Neural Networks and Their Connections to Bisimulation and Logic (AAAI 2024 · similarity 0.87)
- AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs (AAAI 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
