HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level

Link Prediction on Hyper-relational Knowledge Graphs (HKG) is a worthwhile endeavor. HKG consists of hyper-relational facts (H-Facts), composed of a main triple and several auxiliary attribute-value qualifiers, which can effectively represent factually comprehensive information. The internal structure of HKG can be represented as a hypergraph-based representation globally and a semantic sequence-based representation locally. However, existing research seldom simultaneously models the graphical and sequential structure of HKGs, limiting HKGs' representation. To overcome this limitation, we propose a novel Hierarchical Attention model for HKG Embedding (HAHE), including global-level and local-level attention. The global-level attention can model the graphical structure of HKG using hypergraph dual-attention layers, while the local-level attention can learn the sequential structure inside H-Facts via heterogeneous self-attention layers. Experiment results indicate that HAHE achieves state-of-the-art performance in link prediction tasks on HKG standard datasets. In addition, HAHE addresses the issue of HKG multi-position prediction for the first time, increasing the applicability of the HKG link prediction task. Our code is publicly available.

PDF Abstract ACL 2023 PDF ACL 2023 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction JF17K HAHE MRR 0.623 # 1
H@1 0.554 # 1
H@10 0.806 # 1
Link Prediction Temp8 HAHE MRR 0.368 # 1
Hit@1 0.291 # 1
Hit@10 0.516 # 1
Link Prediction Wikipeople HAHE MRR 0.509 # 1
H@1 0.447 # 1
H@10 0.639 # 1


No methods listed for this paper. Add relevant methods here