Mutual Teaching for Graph Convolutional Networks

09/02/2020
by   Kun Zhan, et al.
13

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
05/08/2022

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

The Graph Convolutional Networks (GCNs) have achieved excellent results ...
research
10/07/2022

Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification

In unsupervised person Re-ID, peer-teaching strategy leveraging two netw...
research
06/01/2021

Robust Mutual Learning for Semi-supervised Semantic Segmentation

Recent semi-supervised learning (SSL) methods are commonly based on pseu...
research
01/26/2022

Mitigating the Mutual Error Amplification for Semi-Supervised Object Detection

Semi-supervised object detection (SSOD) has achieved substantial progres...
research
07/04/2018

BayesGrad: Explaining Predictions of Graph Convolutional Networks

Recent advances in graph convolutional networks have significantly impro...
research
11/22/2022

Confidence-guided Centroids for Unsupervised Person Re-Identification

Unsupervised person re-identification (ReID) aims to train a feature ext...
research
08/24/2020

Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID

In this technical report, we present our submission to the VisDA Challen...

Please sign up or login with your details

Forgot password? Click here to reset