Incorporating GAN for Negative Sampling in Knowledge Representation Learning
This work addresses a bottleneck in knowledge graph embedding for AI researchers, offering an incremental improvement over traditional random sampling methods.
The paper tackles the problem of inefficient negative sampling in knowledge representation learning by proposing a GAN-based framework that generates high-quality negative samples, resulting in improved performance on triplets classification and link prediction tasks.
Knowledge representation learning aims at modeling knowledge graph by encoding entities and relations into a low dimensional space. Most of the traditional works for knowledge embedding need negative sampling to minimize a margin-based ranking loss. However, those works construct negative samples through a random mode, by which the samples are often too trivial to fit the model efficiently. In this paper, we propose a novel knowledge representation learning framework based on Generative Adversarial Networks (GAN). In this GAN-based framework, we take advantage of a generator to obtain high-quality negative samples. Meanwhile, the discriminator in GAN learns the embeddings of the entities and relations in knowledge graph. Thus, we can incorporate the proposed GAN-based framework into various traditional models to improve the ability of knowledge representation learning. Experimental results show that our proposed GAN-based framework outperforms baselines on triplets classification and link prediction tasks.