HaSa: Hardness and Structure-Aware Contrastive Knowledge Graph Embedding
Not on the map. Why?
Abstract (arXiv)
We consider a contrastive learning approach to knowledge graph embedding (KGE) via InfoNCE. For KGE, efficient learning relies on augmenting the training data with negative triples. However, most KGE works overlook the bias from generating the negative triples-false negative triples (factual triples missing from the knowledge graph). We argue that the generation of high-quality (i.e., hard) negative triples might lead to an increase in false negative triples. To mitigate the impact of false negative triples during the generation of hard negative triples, we propose the Hardness and Structure-aware (HaSa) contrastive KGE method, which alleviates the effect of false negative triples while generating the hard negative triples. Experiments show that HaSa improves the performance of InfoNCE-based KGE approaches and achieves state-of-the-art results in several metrics for WN18RR datasets and competitive results for FB15k-237 datasets compared to both classic and pre-trained LM-based KGE methods.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 17 May 2023.
Builds on
31 of 45 references.
References · 31
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2020Supervised Contrastive Learningcited by 2,803
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
- 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
- 2016Complex Embeddings for Simple Link Predictioncited by 897
- 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
19 more
- 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
- 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
- 2020Contrastive Learning with Hard Negative Samplescited by 619
- 2020Hard Negative Mixing for Contrastive Learningcited by 399
- 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
- 2020Debiased Contrastive Learningcited by 354
- 2020Contrastive Learning with Adversarial Examplescited by 91
- 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
- 2021ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learningcited by 72
- 2022Knowledge Graph Contrastive Learning for Recommendationcited by 69
- 2020PairRE: Knowledge Graph Embeddings via Paired Relation Vectorscited by 67
- 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
- 2018NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embeddingcited by 42
- 2020Structure Aware Negative Sampling in Knowledge Graphscited by 26
- 2021TempoQR: Temporal Question Reasoning over Knowledge Graphscited by 26
- 2019Relation Embedding with Dihedral Group in Knowledge Graphcited by 25
- 2022Joint Language Semantic and Structure Embedding for Knowledge Graph Completioncited by 15
- 2022KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completioncited by 10
- 2022Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddingscited by 8
Built on by
Citing papers per year: 2024: 3.
3 papers.