To address the insufficient collaborative modeling of local structural information and global path dependencies in knowledge graph completion tasks, we propose MGAT-BiKR, a model that combines multi-layer graph attention networks with bidirectional path reasoning. The multi-layer graph attention network dynamically aggregates the multi-hop neighborhood semantics of target entities. By leveraging a multi-head attention mechanism, it adaptively assigns weights to heterogeneous neighbors, thereby resolving the limitation of traditional methods in identifying key relational contexts. Simultaneously, bidirectional path reasoning is achieved via a BiLSTM encoder combined with path attention, which explicitly captures temporal dependencies in both forward and backward directions across multi-step relational paths. Experiments on the FB15k-237, WN18RR, and NELL995 datasets show that the proposed model achieves Hits@1 scores of 0.986, 0.978, and 0.967 in link prediction tasks. It outperforms the PathCon model by 1.2%, 1.8%, and 12.1%, respectively. This approach efficiently addresses long-tail relationship reasoning in sparse knowledge graphs.

Ao Guo, Guiping Wang, Yingchuan Zhou. Fusing Multi-Layer Graph Attention Networks and Bidirectional Path Reasoning for Knowledge Graph Completion. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 5: 1-9. https://doi.org/10.25236/AJCIS.2025.080501.

[1] Majumdar A, Ajay A, Zhang X, et al. Openeqa: Embodied question answering in the era of foundation models[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024: 16488-16498.

[2] Ko H, Lee S, Park Y, et al. A survey of recommendation systems: recommendation models, techniques, and application fields[J]. Electronics, 2022, 11(1): 141.

[3] Nadkarni P M, Ohno-Machado L, Chapman W W. Natural language processing: an introduction[J]. Journal of the American Medical Informatics Association, 2011, 18(5): 544-551.

[4] Bordes A, Usunier N, Garcia-Duran A, et al. Translating embeddings for modeling multi-relational data[J]. Advances in neural information processing systems, 2013, 26.

[5] Sun Z, Deng Z H, Nie J Y, et al. Rotate: Knowledge graph embedding by relational rotation in complex space[J]. arxiv preprint arxiv:1902.10197, 2019.

[6] Yang B, Yih W, He X, et al. Embedding entities and relations for learning and inference in knowledge bases[J]. arxiv preprint arxiv:1412.6575, 2014.

[7] Trouillon T, Welbl J, Riedel S, et al. Complex embeddings for simple link prediction[C]//International conference on machine learning. PMLR, 2016: 2071-2080.

[8] Lao N, Cohen W W. Relational retrieval using a combination of path-constrained random walks[J]. Machine learning, 2010, 81: 53-67.

[9] Xiong W, Hoang T, Wang W Y. Deeppath: A reinforcement learning method for knowledge graph reasoning[J]. arxiv preprint arxiv:1707.06690, 2017.

[10] Neelakantan A, Roth B, McCallum A. Compositional vector space models for knowledge base completion[J]. arxiv preprint arxiv:1504.06662, 2015.

[11] Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks[C]//The semantic web: 15th international conference, ESWC 2018, Heraklion, Crete, Greece, June 3–7, 2018, proceedings 15. Springer International Publishing, 2018: 593-607.

[12] Li Z, Zhao Y, Zhang Y, et al. Multi-relational graph attention networks for knowledge graph completion[J]. Knowledge-Based Systems, 2022, 251: 109262.

[13] Zhang Z, Zhuang F, Zhu H, et al. Relational graph neural network with hierarchical attention for knowledge graph completion[C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(05): 9612-9619.

[14] Nguyen D Q, Nguyen T D, Nguyen D Q, et al. A novel embedding model for knowledge base completion based on convolutional neural network[J]. arxiv preprint arxiv:1712.02121, 2017.

[15] Dettmers T, Minervini P, Stenetorp P, et al. Convolutional 2d knowledge graph embeddings[C]//Proceedings of the AAAI conference on artificial intelligence. 2018, 32(1).

[16] Zhang S, Tay Y, Yao L, et al. Quaternion knowledge graph embeddings[J]. Advances in neural information processing systems, 2019, 32.

[17] Sadeghian A, Armandpour M, Ding P, et al. Drum: End-to-end differentiable rule mining on knowledge graphs[J]. Advances in neural information processing systems, 2019, 32.

[18] Zhou X, Hui B, Zhang L, et al. A structure distinguishable graph attention network for knowledge base completion[J]. Neural Computing and Applications, 2021, 33(23): 16005-16017.

[19] Wang H, Ren H, Leskovec J. Relational message passing for knowledge graph completion[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021: 1697-1707.