mlsanityData to 14 Oct 2026

Graph Component Contrastive Learning for Concept Relatedness Estimation

arXiv 2206.12556 ↗First posted 25 Jun 2022cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Concept relatedness estimation (CRE) aims to determine whether two given concepts are related. Existing methods only consider the pairwise relationship between concepts, while overlooking the higher-order relationship that could be encoded in a concept-level graph structure. We discover that this underlying graph satisfies a set of intrinsic properties of CRE, including reflexivity, commutativity, and transitivity. In this paper, we formalize the CRE properties and introduce a graph structure named ConcreteGraph. To address the data scarcity issue in CRE, we introduce a novel data augmentation approach to sample new concept pairs from the graph. As it is intractable for data augmentation to fully capture the structural information of the ConcreteGraph due to a large amount of potential concept pairs, we further introduce a novel Graph Component Contrastive Learning framework to implicitly learn the complete structure of the ConcreteGraph. Empirical results on three datasets show significant improvement over the state-of-the-art model. Detailed ablation studies demonstrate that our proposed approach can effectively capture the high-order relationship among concepts.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 25 Jun 2022.

Builds on

29 of 53 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2018Deep contextualized word representationscited by 2,290
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  12. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
17 more
  1. 2020Simple and Deep Graph Convolutional Networkscited by 860
  2. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  3. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  4. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  5. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  6. 2020SelfORE: Self-supervised Relational Feature Learning for Open Relation Extractioncited by 43
  7. 2022COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learningcited by 39
  8. 2020Unsupervised Text Generation by Learning from Searchcited by 36
  9. 2020Semi-supervised Relation Extraction via Incremental Meta Self-Trainingcited by 35
  10. 2020Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Readingcited by 33
  11. 2021Gradient Imitation Reinforcement Learning for Low Resource Relation Extractioncited by 33
  12. 2022HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extractioncited by 32
  13. 2022Text Revision by On-the-Fly Representation Optimizationcited by 17
  14. 2022A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Modelcited by 16
  15. 2019Improving Question Generation With to the Point Contextcited by 15
  16. 2022Graph-adaptive Rectified Linear Unit for Graph Neural Networkscited by 12
  17. 2014Text Relatedness Based on a Word Thesauruscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 0; 2026: 1.

6 papers.

  1. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 279
  2. 2022MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networkscited by 4
  3. 2024Astra: Efficient Transformer Architecture and Contrastive Dynamics Learning for Embodied Instruction Followingcited by 3
  4. 2023VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencodercited by 2
  5. 2023FedHGN: A Federated Framework for Heterogeneous Graph Neural Networkscited by 1
  6. 2026GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completioncited by 0