Papers › Entity Resolution with Hierarchical Graph Attention Networks

Entity Resolution with Hierarchical Graph Attention Networks

1 Jun 2022SIGMOD/PODS 2022 6archive 2025-07-28

Dezhong Yao, Yuhong Gu, Gao Cong, Hai Jin, Xinqiao Lv

Entity Resolution (ER) links entities that refer to the same real-world entity from different sources. Existing work usually takes pairs of entities as input and judges those pairs independently. However, there is often interdependence between different pairs of ER decisions, e.g., the entities from the same data source are usually semantically related to each other. Furthermore, current ER approaches are mainly based on attribute similarity comparison, but ignore interdependence between attributes. To address the limits of existing methods, we propose HierGAT, a new method for ER based on a Hierarchical Graph Attention Transformer Network, which can model and exploit the interdependence between different ER decisions. The benefit of our method comes from: 1) The graph attention network model for joint ER decisions; 2) The graph-attention capability to identify the discriminative words from attributes and find the most discriminative attributes. Furthermore, we propose to learn contextual embeddings to enrich word embeddings for better performance. The experimental results on publicly available benchmark datasets show that HierGAT outperforms DeepMatcher by up to 32.5% of F1 score and up to 8.7% of F1 score compared with Ditto.

PaperPDFCode

Code

CGCL-codes/HierGAT 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

AttributeEntity ResolutionGraph AttentionWord Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Resolution Abt-Buy HG F1 (%) 89.8 #6 of 16 Archive leaderboard report
Entity Resolution Amazon-Google HG F1 (%) 76.4 #6 of 17 Archive leaderboard report
Entity Resolution WDC Computers-small HG F1 (%) 88.50 #3 of 6 Archive leaderboard report
Entity Resolution WDC Computers-xlarge HG F1 (%) 96.50 #4 of 6 Archive leaderboard report
Entity Resolution WDC Watches-small HG F1 (%) 94 #1 of 4 Archive leaderboard report
Entity Resolution WDC Watches-xlarge HG F1 (%) 96.50 #3 of 3 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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