# Mutual Teaching for Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2009.00952 · HTML: https://mlsanity.com/paper/2009.00952/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Informative Pseudo-Labeling for Graph Neural Networks with Few Labels](https://mlsanity.com/paper/2201.07951/) (2022)
- [Distribution Consistency based Self-Training for Graph Neural Networks with Sparse Labels](https://mlsanity.com/paper/2401.10394/) (2024)
- [Graph-based Knowledge Distillation: A survey and experimental evaluation](https://mlsanity.com/paper/2302.14643/) (2023)
- [Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning](https://mlsanity.com/paper/2309.06034/) (2023)
- [Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning](https://mlsanity.com/paper/2104.01711/) (2021)
- [Pseudo Contrastive Learning for Graph-based Semi-supervised Learning](https://mlsanity.com/paper/2302.09532/) (2023)
- [Never Skip a Batch: Dense Learning of Temporal GNNs via Adaptive Pseudo-Supervision](https://mlsanity.com/paper/2505.12526/) (2025)

## Abstract (arXiv)

Graph convolutional networks produce good predictions of unlabeled samples due to its transductive label propagation. Since samples have different predicted confidences, we take high-confidence predictions as pseudo labels to expand the label set so that more samples are selected for updating models. We propose a new training method named as mutual teaching, i.e., we train dual models and let them teach each other during each batch. First, each network feeds forward all samples and selects samples with high-confidence predictions. Second, each model is updated by samples selected by its peer network. We view the high-confidence predictions as useful knowledge, and the useful knowledge of one network teaches the peer network with model updating in each batch. In mutual teaching, the pseudo-label set of a network is from its peer network. Since we use the new strategy of network training, performance improves significantly. Extensive experimental results demonstrate that our method achieves superior performance over state-of-the-art methods under very low label rates.