KBGAN: Adversarial Learning for Knowledge Graph Embeddings

By Liwei Cai, William Yang Wang. North American Chapter of the Association for Computational Linguistics, 2017

322 citations recorded by the source corpus.

We introduce KBGAN, an adversarial learning framework to improve the performances of a wide range of existing knowledge graph embedding models. Because knowledge graphs typically only contain positive facts, sampling useful negative training examples is a nontrivial task. Replacing the head or tail entity of a fact with a uniformly randomly selected entity is a conventional method for generating negative facts, but the majority of the generated negative facts 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. 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/73047a0f0192a35d3b5c6f5ebeadf3706b17e4dc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

GraDA: Graph Generative Data Augmentation for Commonsense Reasoning (2022, background): “, 2000) algorithm and its variants (Yu et al., 2017; Cai and Wang, 2018; Qin et al., 2018; Zhang et al., 2018) to circumvent the discrete sampling issue for text-based GANs.”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “Kbgan [386] is proposed to generate high-quality negative examples and used in knowledge graph embeddings.”
Adaptive Convolution for Multi-Relational Learning (2019, unknown): “(Niepert, 2016), KBGAN (Cai and Wang, 2017), KBLRN (Garcia-Duran and Niepert, 2018), and Node+LinkFeat (Toutanova and Chen, 2015).”
Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion (2020, unknown): “59 KBGAN [5] - - .”
DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction (2018, background): “Both the generator and the discriminator require the pre-training process, which is the common setting for GANs (Cai and Wang, 2017; Wang et al., 2017).”
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space (2018, methodology): “We re-implement a 50- dimension TransE model with the margin-based ranking criterion that was used in (Cai & Wang, 2017), and evaluate its performance on FB15k-237, WN18RR and WN18 with self-adversarial negative sampling.”
KG-BERT: BERT for Knowledge Graph Completion (2019, unknown): “ComplEx could not perform well on WN18RR and FB15k-237, but can be improved using adversarial negative sampling in KBGAN and RotatE.”
Self-Supervised Learning: Generative or Contrastive (2020, background): “[16], [138] leverage adversarial sampling to improve the negative samples’ quality.”
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network (2017, unknown): “4 KBGAN (Cai and Wang, 2018) – 0.”
A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, unknown): “The work in [7] also shows that negative sampling can largely affect the expressiveness of KG embeddings.”
Generative artificial intelligence: a systematic review and applications (2024, unknown): “Cai and Wang [18] introduced KBGAN, an innovative adversarial learning framework designed to enhance the performance of various existing knowledge graph embedding models.”
GraDA: Graph Generative Data Augmentation for Commonsense Reasoning (2022, background): “, 2000) algorithm and its variants (Yu et al., 2017; Cai and Wang, 2018; Qin et al., 2018; Zhang et al., 2018) to circumvent the discrete sampling issue for text-based GANs.”
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions (2019, methodology): “The scores of all the baselines are taken directly from the values reported in the papers (Dettmers et al. 2018; Sun et al. 2019a; Shang et al. 2019; Cai and Wang 2018; García-Durán and Niepert 2018).”
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning (2020, methodology): “In addition our work is also related to using negative samples for effective learning (Cai and Wang, 2018).”
Composition-based Multi-Relational Graph Convolutional Networks (2019, methodology): “The scores of baseline methods are taken directly from the previous papers (Sun et al., 2019; Cai & Wang, 2018; Shang et al., 2019; Balaževi´c et al., 2019; Jiang et al., 2019; Ye et al., 2019).”
Adversarial Contrastive Estimation (2018, background): “Concurrent with our work, there have been other interests in applying the GAN to NLP problems (Fedus et al., 2018; Wang et al., 2018; Cai and Wang, 2017).”