mlsanityData to 14 Oct 2026

Constraint Multi-class Positive and Unlabeled Learning for Distantly Supervised Named Entity Recognition

arXiv 2504.04963 ↗First posted 7 Apr 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data by external knowledge bases instead of human annotations. However, it tends to suffer from a high false negative rate due to the inherent incompleteness. To address this issue, we present a novel approach called Constraint Multi-class Positive and Unlabeled Learning (CMPU), which introduces a constraint factor on the risk estimator of multiple positive classes. It suggests that the constraint non-negative risk estimator is more robust against overfitting than previous PU learning methods with limited positive data. Solid theoretical analysis on CMPU is provided to prove the validity of our approach. Extensive experiments on two benchmark datasets that were labeled using diverse external knowledge sources serve to demonstrate the superior performance of CMPU in comparison to existing DS-NER methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 56 of its 82 references that are in the map. First posted on arXiv 7 Apr 2025.

Builds on

56 of 82 references.

References · 56

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Learning without Forgettingcited by 2,496
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  12. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
38 more
  1. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  2. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  3. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
  4. 2020Few-Shot Class-Incremental Learningcited by 251
  5. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  6. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  7. 2016How to learn a graph from smooth signalscited by 146
  8. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 132
  9. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  10. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 115
  11. 2019Continuous Graph Neural Networkscited by 114
  12. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  13. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  14. 2020Graph Prototypical Networks for Few-shot Learning on Attributed Networkscited by 90
  15. 2020Graph Meta Learning via Local Subgraphscited by 89
  16. 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
  17. 2020Streaming Graph Neural Networks via Continual Learningcited by 64
  18. 2019Graph Few-shot Learning via Knowledge Transfercited by 63
  19. 2020Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Ratescited by 49
  20. 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
  21. 2020Graph Neural Networks with Continual Learning for Fake News Detection from Social Mediacited by 43
  22. 2020GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systemscited by 42
  23. 2021Graph Few-shot Class-incremental Learningcited by 41
  24. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  25. 2019Transductive Zero-Shot Learning with Visual Structure Constraintcited by 36
  26. 2021Continual Learning of Knowledge Graph Embeddingscited by 35
  27. 2020Disentangle-based Continual Graph Representation Learningcited by 25
  28. 2022FreeKD: Free-direction Knowledge Distillation for Graph Neural Networkscited by 23
  29. 2020Lifelong Learning of Graph Neural Networks for Open-World Node Classificationcited by 22
  30. 2022FAITH: Few-Shot Graph Classification with Hierarchical Task Graphscited by 22
  31. 2022Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representationcited by 22
  32. 2018Semi-supervised Learning on Graphs with Generative Adversarial Netscited by 21
  33. 2020Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embeddingcited by 19
  34. 2018Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learningcited by 15
  35. 2021Zero-shot Node Classification with Decomposed Graph Prototype Networkcited by 15
  36. 2023Few-shot Node Classification with Extremely Weak Supervisioncited by 14
  37. 2021Edge: Enriching Knowledge Graph Embeddings with External Textcited by 13
  38. 2021Structured Citation Trend Prediction Using Graph Neural Networkscited by 11

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.