Papers › Multi-modal Siamese Network for Entity Alignment

Multi-modal Siamese Network for Entity Alignment

14 Aug 2022KDD 2022 8archive 2025-07-28

Liyi Chen, Zhi Li, Tong Xu, Han Wu, Zhefeng Wang, Nicholas Jing Yuan, Enhong Chen

The booming of multi-modal knowledge graphs (MMKGs) has raised the imperative demand for multi-modal entity alignment techniques, which facilitate the integration of multiple MMKGs from separate data sources. Unfortunately, prior arts harness multi-modal knowledge only via the heuristic merging of uni-modal feature embeddings. Therefore, inter-modal cues concealed in multi-modal knowledge could be largely ignored. To deal with that problem, in this paper, we propose a novel Multi-modal Siamese Network for Entity Alignment (MSNEA) to align entities in different MMKGs, in which multi-modal knowledge could be comprehensively leveraged by the exploitation of inter-modal effect. Specifically, we first devise a multi-modal knowledge embedding module to extract visual, relational, and attribute features of entities to generate holistic entity representations for distinct MMKGs. During this procedure, we employ inter-modal enhancement mechanisms to integrate visual features to guide relational feature learning and adaptively assign attention weights to capture valuable attributes for alignment. Afterwards, we design a multi-modal contrastive learning module to achieve inter-modal enhancement fusion with avoiding the overwhelming impact of weak modalities. Experimental results on two public datasets demonstrate that our proposed MSNEA provides state-of-the-art performance with a large margin compared with competitive baselines.

PaperPDFCode

Code

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

AttributeContrastive LearningEntity AlignmentKnowledge GraphsMulti-modal Entity AlignmentMulti-modal Knowledge Graph

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-modal Entity Alignment UMVM-dbp-fr-en MSNEA (w/o surf) Hits@1 0.583 #9 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-fr-en MSNEA (w/o surf & w/o iter) Hits@1 0.557 #10 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-ja-en MSNEA (w/o surf) Hits@1 0.557 #9 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-ja-en MSNEA (w/o surf & w/o iter) Hits@1 0.541 #10 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-zh-en MSNEA (w/o surf) Hits@1 0.648 #9 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-zh-en MSNEA (w/o surf & w/o iter) Hits@1 0.609 #10 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v1 MSNEA (w/o surf) Hits@1 0.809 #7 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v1 MSNEA (w/o surf & w/o iter) Hits@1 0.800 #8 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v2 MSNEA (w/o surf) Hits@1 0.862 #7 of 7 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-de MSNEA (w/o surf) Hits@1 0.788 #7 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-de MSNEA (w/o surf & w/o iter) Hits@1 0.753 #8 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-fr MSNEA (w/o surf) Hits@1 0.699 #7 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-fr MSNEA (w/o surf & w/o iter) Hits@1 0.692 #8 of 8 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

ALIGNContrastive LearningSiamese Network

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