Abstract
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 that 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 the 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 significantly outperforms the state-of-the-art methods.
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 that 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 the 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 significantly outperforms the state-of-the-art methods.
Originalsprog | Engelsk |
---|---|
Titel | ACM Web Conference 2023 - Proceedings of the World Wide Web Conference, WWW 2023 |
Antal sider | 11 |
Forlag | Association for Computing Machinery |
Publikationsdato | 30 apr. 2023 |
Sider | 2528–2538 |
ISBN (Elektronisk) | 978-1-4503-9416-1 |
DOI | |
Status | Udgivet - 30 apr. 2023 |
Begivenhed | 2023 World Wide Web Conference, WWW 2023 - Austin, USA Varighed: 30 apr. 2023 → 4 maj 2023 |
Konference
Konference | 2023 World Wide Web Conference, WWW 2023 |
---|---|
Land/Område | USA |
By | Austin |
Periode | 30/04/2023 → 04/05/2023 |
Sponsor | ACM SIGWEB, Amazon Science, Baidu, et al., Megagon Labs, Zhipu AI |
Bibliografisk note
Publisher Copyright:© 2023 ACM.