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

Link Prediction on N-ary Relational Facts: A Graph-based Approach

About

Link prediction on knowledge graphs (KGs) is a key research topic. Previous work mainly focused on binary relations, paying less attention to higher-arity relations although they are ubiquitous in real-world KGs. This paper considers link prediction upon n-ary relational facts and proposes a graph-based approach to this task. The key to our approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention. The fully-connected attention captures universal inter-vertex interactions, while with edge-aware attentive biases to particularly encode the graph structure and its heterogeneity. In this fashion, our approach fully models global and local dependencies in each n-ary fact, and hence can more effectively capture associations therein. Extensive evaluation verifies the effectiveness and superiority of our approach. It performs substantially and consistently better than current state-of-the-art across a variety of n-ary relational benchmarks. Our code is publicly available.

Quan Wang, Haifeng Wang, Yajuan Lyu, Yong Zhu• 2021

Related benchmarks

TaskDatasetResultRank
Entity PredictionWikiPeople (all entities)
MRR47.9
43
Link PredictionWikiPeople
MRR48
24
Hyper-Relational Link PredictionJFFI100 V2
H/T Score0.2957
22
Link PredictionWD50K
MRR0.363
22
Hyper-Relational Link PredictionJFFI100 V1
H/T Metric32.79
22
Hyper-Relational Link PredictionWD20K66 V2
H/T Score31.82
19
Hyper-Relational Link PredictionWD20K33 V1
H/T Score0.2062
19
Hyper-Relational Link PredictionWD20K100 V2
H/T Ratio20.36
19
Hyper-Relational Link PredictionWD20K66 V1
MRR (H/T)0.0176
19
Hyper-Relational Link PredictionJFFI V1
MRR (H/T)0.0487
18
Showing 10 of 38 rows

Other info

Follow for update