Loading [a11y]/accessibility-menu.js
SemSI-GAT: Semantic Similarity-based Interaction Graph Attention Network for Knowledge Graph Completion | IEEE Journals & Magazine | IEEE Xplore
Scheduled Maintenance: On Tuesday, 25 February, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (1800-2200 UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

SemSI-GAT: Semantic Similarity-based Interaction Graph Attention Network for Knowledge Graph Completion


Abstract:

Graph Neural Networks (GNNs) show great power in Knowledge Graph Completion (KGC) as they can handle nonEuclidean graph structures and do not depend on the specific shape...Show More

Abstract:

Graph Neural Networks (GNNs) show great power in Knowledge Graph Completion (KGC) as they can handle nonEuclidean graph structures and do not depend on the specific shape or topology of the graph. However, many current GNNbased KGC models have difficulty in effectively capturing and utilizing the substantial structure and global semantic information in Knowledge Graphs (KGs). For more effective use of GNN for KGC, we innovatively propose the Semantic Similaritybased Interaction Graph Attention Network (SemSI-GAT) for the KGC task. In SemSI-GAT, we utilize BERT, a pre-trained language model, to learn the global semantic information and obtain semantic similarity between entities and their neighbors. Furthermore, we creatively design a novel encoder network called the interaction graph attention network and introduce a semantic similarity sampling mechanism to optimize the aggregation of interaction information between neighbors. By aggregating local features with interaction features, this network can generate more expressive structural embeddings. This network generates more expressive embeddings by fusing global semantic information, local structure features, and interaction features. The experimental evaluations demonstrate that the proposed SemSIGAT outperforms existing state-of-the-art KGC methods on four benchmark datasets
Page(s): 1 - 13
Date of Publication: 13 January 2025

ISSN Information: