Abstract | ||
---|---|---|
Knowledge graph (KG) embedding techniques represent entities and relations as low-dimensional, continuous vectors, and thus enables machine learning models to be easily adapted to KG completion and querying tasks. However, learned dense vectors are inefficient for large-scale similarity computations. Learning-to-hash is to learn compact binary codes from high-dimensional input data and provides a promising way to accelerate efficiency by measuring Hamming distance instead of Euclidean distance or dot-product. Unfortunately, most of learning-to-hash methods cannot be directly applied to KG structure encoding. In this paper, we introduce a novel framework for encoding incomplete KGs and graph queries in Hamming space. To preserve KG structure information from embeddings to hash codes and address the ill-posed gradient issue in optimization, we utilize a continuation method with convergence guarantees to jointly encode queries and KG entities with geometric operations. The hashed embedding of a query can be utilized to discover target answers from incomplete KGs whilst the efficiency has been greatly improved. We compared our model with state-of-the-art methods on real-world KGs. Experimental results show that our framework not only significantly speeds up the searching process, but also provides good results for unanswerable queries caused by incomplete information. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICDM.2019.00174 | 2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019) |
Keywords | Field | DocType |
knowledge graph embedding, learning to hashing, graph query | Data mining,Embedding,Computer science,Euclidean distance,Binary code,Hamming distance,Hash function,Hamming space,Complete information,Encoding (memory) | Conference |
ISSN | Citations | PageRank |
1550-4786 | 2 | 0.42 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Meng Wang | 1 | 24 | 11.05 |
Haomin Shen | 2 | 2 | 0.42 |
Sen Wang | 3 | 477 | 37.24 |
Lina Yao | 4 | 46 | 11.72 |
Yinlin Jiang | 5 | 2 | 0.42 |
Guilin Qi | 6 | 961 | 88.58 |
Yang Chen | 7 | 209 | 29.24 |