Papers › R-GCN: The R Could Stand for Random

R-GCN: The R Could Stand for Random

4 Mar 2022arXiv:2203.02424archive 2025-07-28

Vic Degraeve, Gilles Vandewiele, Femke Ongenae, Sofie Van Hoecke

The inception of the Relational Graph Convolutional Network (R-GCN) marked a milestone in the Semantic Web domain as a widely cited method that generalises end-to-end hierarchical representation learning to Knowledge Graphs (KGs). R-GCNs generate representations for nodes of interest by repeatedly aggregating parameterised, relation-specific transformations of their neighbours. However, in this paper, we argue that the the R-GCN's main contribution lies in this "message passing" paradigm, rather than the learned weights. To this end, we introduce the "Random Relational Graph Convolutional Network" (RR-GCN), which leaves all parameters untrained and thus constructs node embeddings by aggregating randomly transformed random representations from neighbours, i.e., with no learned parameters. We empirically show that RR-GCNs can compete with fully trained R-GCNs in both node classification and link prediction settings.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

predict-idlab/RR-GCN officialmentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Knowledge GraphsLink PredictionNode ClassificationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB15k-237 RR-GCN-PPV Hits@1 0.157 #54 of 75 Archive leaderboard report
Link Prediction FB15k-237 RR-GCN-PPV Hits@10 0.412 #54 of 75 Archive leaderboard report
Link Prediction FB15k-237 RR-GCN-PPV Hits@3 0.256 #54 of 75 Archive leaderboard report
Link Prediction FB15k-237 RR-GCN-PPV MRR 0.238 #54 of 75 Archive leaderboard report
Node Classification AIFB RR-GCN-PPV-CUT Accuracy 95.83 #2 of 7 Archive leaderboard report
Node Classification AIFB RR-GCN-PPV Accuracy 86.11 #7 of 7 Archive leaderboard report
Node Classification AM RR-GCN-PPV-CUT (Unimportant relations removed) Accuracy 91.31 #2 of 8 Archive leaderboard report
Node Classification AM RR-GCN-PPV-CUT Accuracy 84.8 #7 of 8 Archive leaderboard report
Node Classification AM RR-GCN-PPV Accuracy 84.65 #8 of 8 Archive leaderboard report
Node Classification AMPLUS RR-GCN-PPV Accuracy 84.54 #1 of 2 Archive leaderboard report
Node Classification AMPLUS R-GCN Accuracy 83.81 #2 of 2 Archive leaderboard report
Node Classification BGS RR-GCN-PPV-CUT Accuracy 84.14 #5 of 7 Archive leaderboard report
Node Classification BGS RR-GCN-PPV Accuracy 78.97 #7 of 7 Archive leaderboard report
Node Classification DBLP RR-GCN-PPV Accuracy 70.61 #2 of 6 Archive leaderboard report
Node Classification DBLP R-GCN Accuracy 68.51 #3 of 6 Archive leaderboard report
Node Classification DMG777K RR-GCN-PPV Accuracy 63.97 #1 of 2 Archive leaderboard report
Node Classification DMG777K R-GCN Accuracy 62.51 #2 of 2 Archive leaderboard report
Node Classification DMGFULL RR-GCN-PPV Accuracy 63.38 #1 of 2 Archive leaderboard report
Node Classification DMGFULL R-GCN Accuracy 57.52 #2 of 2 Archive leaderboard report
Node Classification MDGENRE R-GCN Accuracy 67.33 #1 of 2 Archive leaderboard report
Node Classification MDGENRE RR-GCN-PPV Accuracy 67.15 #2 of 2 Archive leaderboard report
Node Classification MUTAG RR-GCN-PPV Accuracy 79.41 #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections