Validation and Optimization of Link Prediction in Knowledge Graph Embeddings through Relationship Prediction

DOI: https://doi.org/10.62517/jike.202404323

Author(s)

Yuhu Tao, Huimin Li*, Jianxiao Wang, Lulu Xue

Affiliation(s)

School of Mathematics and Computer Science, Yunnan Minzu University, Kunming, China *Corresponding Author.

Abstract

Common inference tasks in knowledge graphs include link prediction, relation prediction, and entity alignment. Knowledge graph embedding (KGE) has demonstrated its effectiveness for these tasks, with numerous KGE models achieving significant results in this domain. Nevertheless, given the intricate relation patterns in knowledge graphs, KGE models frequently show constrained reasoning capabilities, especially in link prediction. Notably, most KGE models have demonstrated satisfactory performance in relation prediction tasks. Motivated by this observation, this paper evaluates and analyzes relation prediction results for two common KGE models and proposes a novel inference method. Our method leverages relation prediction scores to support and optimize KGE models’ link prediction abilities. Comprehensive and rigorous experiments validate our methodology, achieving competitive results across both benchmark datasets.

Keywords

Knowledge Graph Embedding; Relation Prediction; Link Prediction

References

[1]Miller G A. WordNet: A Lexical Database for English[J]. Communications of ACM, 1995, 38:39-41. [2]Bollacker K D, Evans C, Paritosh P K, et al. Freebase: A Collaboratively Created Graph Database for Structuring Human Knowledge[C]. Proceedings of the SIGMOD Conference, 2008. [3]Zhang Z, Cai J, Zhang, Y,et al. Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(03): 3065-3072. [4]Bordes A,Usunier N, Garcia-Durán A, et al. Translating embeddings for modeling multi-relational data[C]. Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, Lake Tahoe, Nevada, USA, 2013, 2787–2795. [5]Chao L, He J, Wang T, et al. PairRE: Knowledge Graph Embeddings via Paired Relation Vectors[C]. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021, 4360–4369. [6]Sun Z, Deng ZH, Nie JY, et al. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space[C]. International Conference on Learning Representations, 2019. [7]Zhu T, Tan H, Chen X Y, et al. A Transformer-based Knowledge Graph Embedding Model Combining Graph Paths and Local Neighborhood[C]. Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN), 2024, 1-9. [8]Zhang W, Du T, Yang C, et al. A Multimodal Knowledge Graph Representation Learning Method Based on Hyperplane Embedding[C].2024 7th International Conference on Advanced Algorithms and Control Engineering (ICAACE), Shanghai, China, 2024, 434-437.