RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding

Bollegala, Danushka; Hakami, Huda; Yoshida, Yasuhiko; Kawarabayashi, Ken-ichi

doi:10.48550/arxiv.2101.10070

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hits@N MRR MR @1 @3 @10 embedding of the graph attention network, but only consider the entity representation obtained from the weighted walk model, we find that experimental results are comparable to ConvE [13], DistMult [20] and RelWalk [7], resulting from that local graph structure features are captured, denoting the effectiveness of Algorithm 1.…”

Section: Kinshipmentioning

confidence: 78%

“…When we do not use the updated entity [16]. WE REPRODUCE THE RESULTS OF KBGAT, RELWALK AND COMPGCN USING [28], [7] AND [18] RESPECTIVELY.…”

Section: Ablation Studymentioning

confidence: 99%

“…This gives rise to more feasible approaches of path sampling, which often relies on heuristics or prior knowledge but underutilizes semantic information in a KG. Such approaches include Node2Vec [6], RelWalk [7] and so on.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Embedding Knowledge Graphs with Semantic-Guided Walk

Tang¹,

Liu²,

Xu³

et al. 2022

Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Knowledge graph completion can complete knowledge by predicting missing facts, which is a increasingly hot research topic in knowledge graph construction. Prevalent approaches propose to embed knowledge graphs in a lowdimensional vector space and use these embedding to predict, but they neglect either semantic information or graph structures. We propose a new approach to knowledge graph completion named as ATTWALK, which learns embedding by exploiting both structural and semantic features of a knowledge graph. This is achieved by leveraging a key insight that an entities' embedding is influenced by its multi-hop neighbors', which can be further distinguished by their semantic importance to the entity. ATTWALK orchestrates a two-step workflow by first evaluating neighbors' semantic weights using graph attention networks for each entity, then exploring the entities' local structural features by performing a semantic weight guided walk. We evaluate ATTWALK by conducting extensive experiments, which show that ATTWALK outperforms 12 representative approaches on average across 3 publicly available datasets.

show abstract

Section: Kinshipmentioning

confidence: 78%

“…When we do not use the updated entity [16]. WE REPRODUCE THE RESULTS OF KBGAT, RELWALK AND COMPGCN USING [28], [7] AND [18] RESPECTIVELY.…”

Section: Ablation Studymentioning

confidence: 99%