AutoSF: Searching Scoring Functions for Knowledge Graph Embedding

26 Apr 2019  ·  Yongqi Zhang, Quanming Yao, Wenyuan Dai, Lei Chen ·

Scoring functions (SFs), which measure the plausibility of triplets in knowledge graph (KG), have become the crux of KG embedding. Lots of SFs, which target at capturing different kinds of relations in KGs, have been designed by humans in recent years... However, as relations can exhibit complex patterns that are hard to infer before training, none of them can consistently perform better than others on existing benchmark data sets. In this paper, inspired by the recent success of automated machine learning (AutoML), we propose to automatically design SFs (AutoSF) for distinct KGs by the AutoML techniques. However, it is non-trivial to explore domain-specific information here to make AutoSF efficient and effective. We firstly identify a unified representation over popularly used SFs, which helps to set up a search space for AutoSF. Then, we propose a greedy algorithm to search in such a space efficiently. The algorithm is further sped up by a filter and a predictor, which can avoid repeatedly training SFs with same expressive ability and help removing bad candidates during the search before model training. Finally, we perform extensive experiments on benchmark data sets. Results on link prediction and triplets classification show that the searched SFs by AutoSF, are KG dependent, new to the literature, and outperform the state-of-the-art SFs designed by humans. read more

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction FB15k AutoKGE MRR 0.861 # 1
Hits@10 0.914 # 1
Link Prediction FB15k-237 AutoKGE MRR 0.365 # 9
Hits@10 0.555 # 8
Link Prediction WN18 AutoKGE MRR 0.952 # 3
Hits@10 0.961 # 2
Link Prediction WN18RR AutoSF MRR 0.490 # 9
Hits@10 0.567 # 15


No methods listed for this paper. Add relevant methods here