KBGAN: Adversarial Learning for Knowledge Graph Embeddings

11/11/2017
by   Liwei Cai, et al.
0

We introduce an adversarial learning framework, which we named KBGAN, to improve the performances of a wide range of existing knowledge graph embedding models. Because knowledge graph datasets typically only contain positive facts, sampling useful negative training examples is a non-trivial task. Replacing the head or tail entity of a fact with a uniformly randomly selected entity is a conventional method for generating negative facts used by many previous works, but the majority of negative facts generated in this way can be easily discriminated from positive facts, and will contribute little towards the training. Inspired by generative adversarial networks (GANs), we use one knowledge graph embedding model as a negative sample generator to assist the training of our desired model, which acts as the discriminator in GANs. The objective of the generator is to generate difficult negative samples that can maximize their likeliness determined by the discriminator, while the discriminator minimizes its training loss. This framework is independent of the concrete form of generator and discriminator, and therefore can utilize a wide variety of knowledge graph embedding models as its building blocks. In experiments, we adversarially train two translation-based models, TransE and TransD, each with assistance from one of the two probability-based models, DistMult and ComplEx. We evaluate the performances of KBGAN on the link prediction task, using three knowledge base completion datasets: FB15k-237, WN18 and WN18RR. Experimental results show that adversarial training substantially improves the performances of target embedding models under various settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/04/2022

Wasserstein Adversarial Learning based Temporal Knowledge Graph Embedding

Research on knowledge graph embedding (KGE) has emerged as an active fie...
research
09/23/2018

Incorporating GAN for Negative Sampling in Knowledge Representation Learning

Knowledge representation learning aims at modeling knowledge graph by en...
research
04/12/2020

Exploring Effects of Random Walk Based Minibatch Selection Policy on Knowledge Graph Completion

In this paper, we have explored the effects of different minibatch sampl...
research
05/02/2022

Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion

Most real-world knowledge graphs (KG) are far from complete and comprehe...
research
03/28/2020

Mining Implicit Entity Preference from User-Item Interaction Data for Knowledge Graph Completion via Adversarial Learning

The task of Knowledge Graph Completion (KGC) aims to automatically infer...
research
01/07/2022

Stay Positive: Knowledge Graph Embedding Without Negative Sampling

Knowledge graphs (KGs) are typically incomplete and we often wish to inf...
research
06/15/2023

Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion

Few-shot knowledge graph completion (FKGC) task aims to predict unseen f...

Please sign up or login with your details

Forgot password? Click here to reset