mlsanityData to 7 Oct 2026

Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning

arXiv 2106.05221 ↗First posted 8 Jun 2021cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph convolutional network (GCN) has become popular in various natural language processing (NLP) tasks with its superiority in long-term and non-consecutive word interactions. However, existing single-hop graph reasoning in GCN may miss some important non-consecutive dependencies. In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer. To alleviate the over-smoothing in high-order Chebyshev approximation, a multi-vote-based cross-attention (MVCAttn) with linear computation complexity is also proposed. The empirical results on four transductive and inductive NLP tasks and the ablation study verify the efficacy of the proposed model. Our source code is available at https://github.com/MathIsAll/HDGCN-pytorch.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

33 of 42 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2017Graph Attention Networkscited by 8,854
  4. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  5. 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
  6. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  7. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  8. 2020Simple and Deep Graph Convolutional Networkscited by 857
  9. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  10. 2020A Generalization of Transformer Networks to Graphscited by 653
  11. 2020Deep Graph Contrastive Representation Learningcited by 535
  12. 2019Graph Transformer Networkscited by 520
21 more
  1. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  2. 2018Graph Convolutional Networks for Text Classificationcited by 345
  3. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  4. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  5. 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 253
  6. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  7. 2020Graph-Bert: Only Attention is Needed for Learning Graph Representationscited by 176
  8. 2019Star-Transformercited by 94
  9. 2020Heterogeneous Graph Neural Networks for Extractive Document Summarizationcited by 90
  10. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
  11. 2020Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networkscited by 77
  12. 2020Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Datacited by 50
  13. 2019Attentional Encoder Network for Targeted Sentiment Classificationcited by 48
  14. 2018Attention Models in Graphs: A Surveycited by 41
  15. 2019GraphNAS: Graph Neural Architecture Search with Reinforcement Learningcited by 41
  16. 2020The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understandingcited by 28
  17. 2018Investigating Capsule Networks with Dynamic Routing for Text Classificationcited by 23
  18. 2019GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animationcited by 21
  19. 2019Spectral Clustering with Graph Neural Networks for Graph Poolingcited by 16
  20. 2019Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classificationcited by 13
  21. 2020Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classificationcited by 2

Built on by

Not cited yet.