NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding

16 Dec 2018  ·  Yongqi Zhang, Quanming Yao, Yingxia Shao, Lei Chen ·

Knowledge Graph (KG) embedding is a fundamental problem in data mining research with many real-world applications. It aims to encode the entities and relations in the graph into low dimensional vector space, which can be used for subsequent algorithms. Negative sampling, which samples negative triplets from non-observed ones in the training data, is an important step in KG embedding. Recently, generative adversarial network (GAN), has been introduced in negative sampling. By sampling negative triplets with large scores, these methods avoid the problem of vanishing gradient and thus obtain better performance. However, using GAN makes the original model more complex and hard to train, where reinforcement learning must be used. In this paper, motivated by the observation that negative triplets with large scores are important but rare, we propose to directly keep track of them with the cache. However, how to sample from and update the cache are two important questions. We carefully design the solutions, which are not only efficient but also achieve a good balance between exploration and exploitation. In this way, our method acts as a "distilled" version of previous GA-based methods, which does not waste training time on additional parameters to fit the full distribution of negative triplets. The extensive experiments show that our method can gain significant improvement in various KG embedding models, and outperform the state-of-the-art negative sampling methods based on GAN.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction FB15k ComplEx NSCaching Hits@10 0.8682 # 5
MR 82 # 5
MRR 0.7721 # 5
Link Prediction FB15k ComplEx NSCaching MRR 0.7721 # 16
Link Prediction FB15k-237 ComplEx NSCaching MRR 0.3021 # 55
Hits@10 0.4805 # 54
MR 221 # 24
Link Prediction WN18 ComplEx NSCaching MRR 0.9355 # 24
Hits@10 0.9398 # 29
MR 1072 # 21
Link Prediction WN18RR ComplEx NSCaching MRR 0.4463 # 57
Hits@10 0.5089 # 66
MR 5365 # 28

Methods