Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Jie, Chen, Hanzhu, Lv, Qitan, Shi, Zhihao, Chen, Jiajun, He, Huarui, Xie, Hongtao, Lian, Defu, Chen, Enhong, Wu, Feng
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914917923160064
author Wang, Jie
Chen, Hanzhu
Lv, Qitan
Shi, Zhihao
Chen, Jiajun
He, Huarui
Xie, Hongtao
Lian, Defu
Chen, Enhong
Wu, Feng
author_facet Wang, Jie
Chen, Hanzhu
Lv, Qitan
Shi, Zhihao
Chen, Jiajun
He, Huarui
Xie, Hongtao
Lian, Defu
Chen, Enhong
Wu, Feng
contents Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity-independent manner. Many popular methods mainly focus on modeling graph-level features, while the edge-level interactions -- especially the semantic correlations between relations -- have been less explored. However, we notice a desirable property of semantic correlations between relations is that they are inherently edge-level and entity-independent. This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task. Inspired by this observation, we propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations that are highly correlated to their topological structures within subgraphs. Specifically, we prove that semantic correlations between any two relations can be categorized into seven topological patterns, and then proposes Relational Correlation Network (RCN) to learn the importance of each pattern. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph that can effectively preserve complete topological patterns within the subgraph. Extensive experiments demonstrate that TACO effectively unifies the graph-level information and edge-level interactions to jointly perform reasoning, leading to a superior performance over existing state-of-the-art methods for the inductive link prediction task.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11528
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
Wang, Jie
Chen, Hanzhu
Lv, Qitan
Shi, Zhihao
Chen, Jiajun
He, Huarui
Xie, Hongtao
Lian, Defu
Chen, Enhong
Wu, Feng
Artificial Intelligence
Inductive link prediction -- where entities during training and inference stages can be different -- has shown great potential for completing evolving knowledge graphs in an entity-independent manner. Many popular methods mainly focus on modeling graph-level features, while the edge-level interactions -- especially the semantic correlations between relations -- have been less explored. However, we notice a desirable property of semantic correlations between relations is that they are inherently edge-level and entity-independent. This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task. Inspired by this observation, we propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations that are highly correlated to their topological structures within subgraphs. Specifically, we prove that semantic correlations between any two relations can be categorized into seven topological patterns, and then proposes Relational Correlation Network (RCN) to learn the importance of each pattern. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph that can effectively preserve complete topological patterns within the subgraph. Extensive experiments demonstrate that TACO effectively unifies the graph-level information and edge-level interactions to jointly perform reasoning, leading to a superior performance over existing state-of-the-art methods for the inductive link prediction task.
title Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2309.11528