Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Unsupervised Entity Alignment for Temporal Knowledge Graphs

About

Entity alignment (EA) is a fundamental data integration task that identifies equivalent entities between different knowledge graphs (KGs). Temporal Knowledge graphs (TKGs) extend traditional knowledge graphs by introducing timestamps, which have received increasing attention. State-of-the-art time-aware EA studies have suggested that the temporal information of TKGs facilitates the performance of EA. However, existing studies have not thoroughly exploited the advantages of temporal information in TKGs. Also, they perform EA by pre-aligning entity pairs, which can be labor-intensive and thus inefficient. In this paper, we present DualMatch which effectively fuses the relational and temporal information for EA. DualMatch transfers EA on TKGs into a weighted graph matching problem. More specifically, DualMatch is equipped with an unsupervised method, which achieves EA without necessitating seed alignment. DualMatch has two steps: (i) encoding temporal and relational information into embeddings separately using a novel label-free encoder, Dual-Encoder; and (ii) fusing both information and transforming it into alignment using a novel graph-matching-based decoder, GM-Decoder. DualMatch is able to perform EA on TKGs with or without supervision, due to its capability of effectively capturing temporal information. Extensive experiments on three real-world TKG datasets offer the insight that DualMatch outperforms the state-of-the-art methods in terms of H@1 by 2.4% - 10.7% and MRR by 1.7% - 7.6%, respectively.

Xiaoze Liu, Junyang Wu, Tianyi Li, Lu Chen, Yunjun Gao• 2023

Related benchmarks

TaskDatasetResultRank
Entity AlignmentDICEWS-1K Normal Setting (10% seeds) (test)
H@195.3
14
Entity AlignmentWY50K-5K Normal Setting (10% seeds) (test)
H@198.1
14
Entity AlignmentDICEWS-200 Less Seed Setting (test)
H@195.3
13
Entity AlignmentWY50K-1K Less Seed Setting (test)
H@194.7
13
Temporal Entity AlignmentDICEWS 200
MRR0.961
11
Temporal Entity AlignmentYAGO-WIKI50K 1K
MRR96.1
11
Temporal Entity AlignmentDICEWS 1K
MRR96.1
10
Temporal Entity AlignmentYAGO-WIKI180K Dense-tem (6.6%) 2000 seeds
MRR91.2
10
Temporal Entity AlignmentBETA (10% seeds)
Hits@165
10
Temporal Entity AlignmentBETA (30% seeds)
H@168.9
10
Showing 10 of 16 rows

Other info

Code

Follow for update