Incorporating GAN for Negative Sampling in Knowledge Representation Learning

Abstract

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.

Accepted to AAAI 2018

Cited by in corpus (14)

• Efficiently Embedding Dynamic Knowledge Graphs
• Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
• LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction
• On the Role of Conceptualization in Commonsense Knowledge Graph Construction
• An Adversarial Transfer Network for Knowledge Representation Learning
• Efficient, Simple and Automated Negative Sampling for Knowledge Graph Embedding
• Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
• NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding
• Evaluating the Effectiveness of Margin Parameter when Learning Knowledge Embedding Representation for Domain-specific Multi-relational Categorized Data
• Unsupervised Path Representation Learning with Curriculum Negative Sampling
• Learning Structured Embeddings of Knowledge Graphs with Adversarial Learning Framework
• Mining Implicit Entity Preference from User-Item Interaction Data for Knowledge Graph Completion via Adversarial Learning
• Towards Fast Evaluation of Unsupervised Link Prediction by Random Sampling Unobserved Links
• On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions