Papers › MoCoSA: Momentum Contrast for Knowledge Graph Completion with Structure-Augmented...

MoCoSA: Momentum Contrast for Knowledge Graph Completion with Structure-Augmented Pre-trained Language Models

16 Aug 2023arXiv:2308.08204archive 2025-07-28

Jiabang He, Liu Jia, Lei Wang, Xiyao Li, Xing Xu

Knowledge Graph Completion (KGC) aims to conduct reasoning on the facts within knowledge graphs and automatically infer missing links. Existing methods can mainly be categorized into structure-based or description-based. On the one hand, structure-based methods effectively represent relational facts in knowledge graphs using entity embeddings. However, they struggle with semantically rich real-world entities due to limited structural information and fail to generalize to unseen entities. On the other hand, description-based methods leverage pre-trained language models (PLMs) to understand textual information. They exhibit strong robustness towards unseen entities. However, they have difficulty with larger negative sampling and often lag behind structure-based methods. To address these issues, in this paper, we propose Momentum Contrast for knowledge graph completion with Structure-Augmented pre-trained language models (MoCoSA), which allows the PLM to perceive the structural information by the adaptable structure encoder. To improve learning efficiency, we proposed momentum hard negative and intra-relation negative sampling. Experimental results demonstrate that our approach achieves state-of-the-art performance in terms of mean reciprocal rank (MRR), with improvements of 2.5% on WN18RR and 21% on OpenBG500.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Entity EmbeddingsKnowledge Graph CompletionKnowledge GraphsLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB15k-237 MoCoSA Hits@1 0.292 #8 of 75 Archive leaderboard report
Link Prediction FB15k-237 MoCoSA Hits@10 0.578 #8 of 75 Archive leaderboard report
Link Prediction FB15k-237 MoCoSA Hits@3 0.42 #8 of 75 Archive leaderboard report
Link Prediction FB15k-237 MoCoSA MRR 0.387 #8 of 75 Archive leaderboard report
Link Prediction OpenBG500 MoCoSA Hits@1 0.531 #1 of 1 Archive leaderboard report
Link Prediction OpenBG500 MoCoSA Hits@10 0.83 #1 of 1 Archive leaderboard report
Link Prediction OpenBG500 MoCoSA Hits@3 0.711 #1 of 1 Archive leaderboard report
Link Prediction OpenBG500 MoCoSA MRR 0.634 #1 of 1 Archive leaderboard report
Link Prediction WN18RR MoCoSA Hits@1 0.624 #3 of 75 Archive leaderboard report
Link Prediction WN18RR MoCoSA Hits@10 0.82 #3 of 75 Archive leaderboard report
Link Prediction WN18RR MoCoSA Hits@3 0.737 #3 of 75 Archive leaderboard report
Link Prediction WN18RR MoCoSA MRR 0.696 #3 of 75 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.

Methods

fail

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