mlsanityData to 7 Oct 2026

Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction

arXiv 2312.04815 ↗First posted 8 Dec 2023cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The rapid development of graph neural networks (GNNs) encourages the rising of link prediction, achieving promising performance with various applications. Unfortunately, through a comprehensive analysis, we surprisingly find that current link predictors with dynamic negative samplers (DNSs) suffer from the migration phenomenon between "easy" and "hard" samples, which goes against the preference of DNS of choosing "hard" negatives, thus severely hindering capability. Towards this end, we propose the MeBNS framework, serving as a general plugin that can potentially improve current negative sampling based link predictors. In particular, we elaborately devise a Meta-learning Supported Teacher-student GNN (MST-GNN) that is not only built upon teacher-student architecture for alleviating the migration between "easy" and "hard" samples but also equipped with a meta learning based sample re-weighting module for helping the student GNN distinguish "hard" samples in a fine-grained manner. To effectively guide the learning of MST-GNN, we prepare a Structure enhanced Training Data Generator (STD-Generator) and an Uncertainty based Meta Data Collector (UMD-Collector) for supporting the teacher and student GNN, respectively. Extensive experiments show that the MeBNS achieves remarkable performance across six link prediction benchmark datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 8 Dec 2023.

Builds on

32 of 54 references.

References · 32

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  8. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  9. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  12. 2018Link Prediction Based on Graph Neural Networkscited by 829
20 more
  1. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  2. 2019Neural Graph Collaborative Filteringcited by 660
  3. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  4. 2020Hard Negative Mixing for Contrastive Learningcited by 399
  5. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  6. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  7. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  8. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  9. 2017IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Modelscited by 75
  10. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  11. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  12. 2020Understanding Negative Sampling in Graph Representation Learningcited by 66
  13. 2017KBGAN: Adversarial Learning for Knowledge Graph Embeddingscited by 62
  14. 2020Reinforced Negative Sampling over Knowledge Graph for Recommendationcited by 40
  15. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  16. 2020Structure Aware Negative Sampling in Knowledge Graphscited by 26
  17. 2020Few-shot link prediction via graph neural networks for Covid-19 drug-repurposingcited by 21
  18. 2018Word2Vec applied to Recommendation: Hyperparameters Mattercited by 20
  19. 2016Hard Negative Mining for Metric Learning Based Zero-Shot Classificationcited by 18
  20. 2020SamWalker++: recommendation with informative sampling strategycited by 5

Built on by

Not cited yet.