AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs

Xingyue Huang, Miguel Romero Orth, Ismail Ilkan Ceylan, Pablo Barcelo

NeurIPS 2023 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings

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 changedWhereMeasuredEffect
Switch history from f(t)=0 to f(t)=t (ablation)C-MPNN architectures · WN18RR and FB15k-237 inductive splitsHits@10No clear effect
Use Msg2 instead of Msg1 or Msg3 (ablation)C-MPNN · FB15k-237 inductive splitsHits@10Hurt
Use Msg2 instead of other message functions (ablation)C-MPNN · WN18RR inductive splitsHits@10No clear effect
Use PNA rather than sum aggregation (ablation)C-MPNN with Msg1 · FB15k-237 inductive splitsHits@10Improved
Use PNA rather than sum aggregation (ablation)C-MPNN with Msg2 or Msg3 · FB15k-237 inductive splitsHits@10Hurt
Use PNA rather than sum aggregation (ablation)C-MPNN · WN18RR inductive splitsHits@10Mixed
Use an initialization that fails target node distinguishability (ablation)C-MPNN · Inductive link predictionHits@10Hurt
Add a global readout (ablation)C-MPNN · WN18RR inductive splitsHits@10No clear effect
Add a global readout (ablation)C-MPNN · FB15k-237 v2 and v4Hits@10: 0.949 -> 0.897; 0.954 -> 0.864Hurt
Use relation-specific readout instead of no readout (ablation)C-MPNN · FB15k-237 v1-v4Hits@10: 0.804 -> 0.835; 0.949 -> 0.959; 0.945 -> 0.953; 0.954 -> 0.960Improved
Use relation-specific readout instead of no readout (ablation)C-MPNN · WN18RR v1-v4Hits@10: 0.941 -> 0.932; 0.895 -> 0.885; 0.904 -> 0.882; 0.886 -> 0.874Hurt
Condition representations on a source node to produce pairwise representationsC-MPNN versus R-MPNN · Transductive link prediction and biomedical knowledgeHits@10Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy