Papers › Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities

Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities

1 Jun 2021ECML PKDD 2021 6archive 2025-07-28

Afshin Sadeghi, Diego Collarana, Damien Graux, Jens Lehmann

Knowledge graphs embeddings (KGE) are lately at the center of many artificial intelligence studies due to their applicability for solving downstream tasks, including link prediction and node classification. However, most Knowledge Graph embedding models encode, into the vector space, only the local graph structure of an entity, i.e., information of the 1-hop neighborhood. Capturing not only local graph structure but global features of entities are crucial for prediction tasks on Knowledge Graphs. This work proposes a novel KGE method named Graph Feature Attentive Neural Network (GFA-NN) that computes graphical features of entities. As a consequence, the resulting embeddings are attentive to two types of global network features. First, nodes’ relative centrality is based on the observation that some of the entities are more “prominent” than the others. Second, the relative position of entities in the graph. GFA-NN computes several centrality values per entity, generates a random set of reference nodes’ entities, and computes a given entity’s shortest path to each entity in the reference set. It then learns this information through optimization of objectives specified on each of these features. We investigate GFA-NN on several link prediction benchmarks in the inductive and transductive setting and show that GFA-NN achieves on-par or better results than state-of-the-art KGE solutions.

PaperPDFCode

Code

afshinsadeghi/GFA-NN mentioned in paperpytorch 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

Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink PredictionLink Property PredictionNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB15k-237 GFA-NN Hits@10 0.522 #64 of 75 Archive leaderboard report
Link Prediction FB15k-237 GFA-NN MR 186 #64 of 75 Archive leaderboard report
Link Prediction FB15k-237 GFA-NN MRR 0.338 #64 of 75 Archive leaderboard report
Link Prediction WN18RR GFA-NN Hits@10 0.575 #34 of 75 Archive leaderboard report
Link Prediction WN18RR GFA-NN MR 3390 #34 of 75 Archive leaderboard report
Link Prediction WN18RR GFA-NN MRR 0.486 #34 of 75 Archive leaderboard report
Link Property Prediction ogbl-biokg GFA-NN Test MRR 0.9011 #2 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg GFA-NN Validation MRR 0.9011 #2 of 16 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