This paper proposes a discrete knowledge graph (KG) embedding (DKGE) method, which projects KG entities and relations into the Hamming space based on a computationally tractable discrete optimization algorithm, to solve the formidable storage and computation cost challenges in traditional continuous graph embedding methods. The convergence of DKGE can be guaranteed theoretically. Extensive experiments demonstrate that DKGE achieves superior accuracy than classical hashing functions that map the effective continuous embeddings into discrete codes. Besides, DKGE reaches comparable accuracy with much lower computational complexity and storage compared to many continuous graph embedding methods.
@article{arxiv.2101.04817,
title = {Discrete Knowledge Graph Embedding based on Discrete Optimization},
author = {Yunqi Li and Shuyuan Xu and Bo Liu and Zuohui Fu and Shuchang Liu and Xu Chen and Yongfeng Zhang},
journal= {arXiv preprint arXiv:2101.04817},
year = {2021}
}
Comments
Accepted at the AAAI-20 Workshop on Knowledge Discovery from Unstructured Data in Financial Services