Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.03947 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916870424100864 |
|---|---|
| author | Hoang-Minh, Thanh |
| author_facet | Hoang-Minh, Thanh |
| contents | Knowledge graphs offer a structured representation of real-world entities and their relationships, enabling a wide range of applications from information retrieval to automated reasoning. In this paper, we conduct a systematic comparison between traditional rule-based approaches and modern deep learning methods for link prediction. We focus on KBGAT, a graph neural network model that leverages multi-head attention to jointly encode both entity and relation features within local neighborhood structures. To advance this line of research, we introduce \textbf{GCAT} (Graph Collaborative Attention Network), a refined model that enhances context aggregation and interaction between heterogeneous nodes. Experimental results on four widely-used benchmark datasets demonstrate that GCAT not only consistently outperforms rule-based methods but also achieves competitive or superior performance compared to existing neural embedding models. Our findings highlight the advantages of attention-based architectures in capturing complex relational patterns for knowledge graph completion tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs Hoang-Minh, Thanh Machine Learning Knowledge graphs offer a structured representation of real-world entities and their relationships, enabling a wide range of applications from information retrieval to automated reasoning. In this paper, we conduct a systematic comparison between traditional rule-based approaches and modern deep learning methods for link prediction. We focus on KBGAT, a graph neural network model that leverages multi-head attention to jointly encode both entity and relation features within local neighborhood structures. To advance this line of research, we introduce \textbf{GCAT} (Graph Collaborative Attention Network), a refined model that enhances context aggregation and interaction between heterogeneous nodes. Experimental results on four widely-used benchmark datasets demonstrate that GCAT not only consistently outperforms rule-based methods but also achieves competitive or superior performance compared to existing neural embedding models. Our findings highlight the advantages of attention-based architectures in capturing complex relational patterns for knowledge graph completion tasks. |
| title | Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.03947 |