mlsanityData to 7 Oct 2026

Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks

arXiv 2205.03753 ↗First posted 8 May 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The Graph Convolutional Networks (GCNs) have achieved excellent results in node classification tasks, but the model's performance at low label rates is still unsatisfactory. Previous studies in Semi-Supervised Learning (SSL) for graph have focused on using network predictions to generate soft pseudo-labels or instructing message propagation, which inevitably contains the incorrect prediction due to the over-confident in the predictions. Our proposed Dual-Channel Consistency based Graph Convolutional Networks (DCC-GCN) uses dual-channel to extract embeddings from node features and topological structures, and then achieves reliable low-confidence and high-confidence samples selection based on dual-channel consistency. We further confirmed that the low-confidence samples obtained based on dual-channel consistency were low in accuracy, constraining the model's performance. Unlike previous studies ignoring low-confidence samples, we calibrate the feature embeddings of the low-confidence samples by using the neighborhood's high-confidence samples. Our experiments have shown that the DCC-GCN can more accurately distinguish between low-confidence and high-confidence samples, and can also significantly improve the accuracy of low-confidence samples. We conducted extensive experiments on the benchmark datasets and demonstrated that DCC-GCN is significantly better than state-of-the-art baselines at different label rates.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 8 May 2022.

Builds on

29 of 47 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  7. 2019Heterogeneous Graph Attention Networkcited by 732
  8. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  9. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  10. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  11. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  12. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
17 more
  1. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  2. 2020Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learningcited by 190
  3. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  4. 2018Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecastingcited by 145
  5. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  6. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  7. 2018Attention-based Graph Neural Network for Semi-supervised Learningcited by 100
  8. 2021Trusted Multi-View Classificationcited by 94
  9. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  10. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  11. 2020Intra Order-preserving Functions for Calibration of Multi-Class Neural Networkscited by 65
  12. 2022Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shiftcited by 38
  13. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  14. 2021Self-supervised Consensus Representation Learning for Attributed Graphcited by 15
  15. 2020Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputscited by 11
  16. 2020Label-Consistency based Graph Neural Networks for Semi-supervised Node Classificationcited by 11
  17. 2020Graph Inference Learning for Semi-supervised Classificationcited by 4

Built on by

Not cited yet.