mlsanityData to 14 Oct 2026

Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networks

arXiv 2205.08625 ↗First posted 17 May 2022cs.CL cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

We present a generic and trend-aware curriculum learning approach for graph neural networks. It extends existing approaches by incorporating sample-level loss trends to better discriminate easier from harder samples and schedule them for training. The model effectively integrates textual and structural information for relation extraction in text graphs. Experimental results show that the model provides robust estimations of sample difficulty and shows sizable improvement over the state-of-the-art approaches across several datasets.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 25 of its 53 references that are in the map. First posted on arXiv 17 May 2022.

Builds on

25 of 53 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2020Longformer: The Long-Document Transformercited by 3,413
  8. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  9. 2018Link Prediction Based on Graph Neural Networkscited by 832
  10. 2014Distributed Representations of Sentences and Documentscited by 678
  11. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  12. 2019Multi-scale Attributed Node Embeddingcited by 548
13 more
  1. 2018Graph Convolutional Networks for Text Classificationcited by 345
  2. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  3. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  4. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  5. 2017Cross-Sentence N-ary Relation Extraction with Graph LSTMscited by 101
  6. 2020Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networkscited by 77
  7. 2020Subgraph Neural Networkscited by 73
  8. 2017Graph Convolutional Encoders for Syntax-aware Neural Machine Translationcited by 70
  9. 2016Distant Supervision for Relation Extraction beyond the Sentence Boundarycited by 62
  10. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  11. 2015Classifying Relations by Ranking with Convolutional Neural Networkscited by 33
  12. 2018Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networkscited by 30
  13. 2019A Silver Standard Corpus of Human Phenotype-Gene Relationscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 1; 2025: 1; 2026: 1.

9 papers.

  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2023MultiDelete for Multimodal Machine Unlearningcited by 20
  3. 2023Curriculum Graph Machine Learning: A Surveycited by 15
  4. 2023Complexity-Guided Curriculum Learning for Text Graphscited by 3
  5. 2023Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approachcited by 2
  6. 2023HuCurl: Human-induced Curriculum Discoverycited by 1
  7. 2024CPT: Competence-progressive Training Strategy for Few-shot Node Classificationcited by 0
  8. 2025FairFlow: Mitigating Dataset Biases through Undecided Learningcited by 0
  9. 2026Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomycited by 0