Can I read Proceedings of the ACM Web Conference 2022 on EtoBox?

Proceedings of the ACM Web Conference 2022 by Liu, Hongrui (author);Hu, Binbin (author);Wang, Xiao (author);Shi, Chuan (author);Zhang, Zhiqiang (author);Zhou, Jun (author) is a scholarly article available to read on EtoBox.

What is Proceedings of the ACM Web Conference 2022 about?

Graph Convolutional Networks (GCNs) have recently attracted vast interest and achieved state-of-the-art performance on graphs, but its success could typically hinge on careful training with amounts of expensive and time-consuming labeled data. To alleviate labeled data scarcity, self-training methods have been widely adopted on graphs by labeling high-confidence unlabeled nodes and then adding them to the training step. In this line, we empirically make a thorough study for current self-training methods on graphs. Surprisingly, we find that high-confidence unlabeled nodes are not always useful, and even introduce the distribution shift issue between the original labeled dataset and the augmented dataset by self-training, severely hindering the capability of self-training on graphs. To this end, in this paper, we propose a novel Distribution Recovered Graph Self-Training framework (DR-GST), which could recover the distribution of the original labeled dataset. Specifically, we first prove the equality of loss function in self-training framework under the distribution shift case and the population distribution if each pseudo-labeled node is weighted by a proper coefficient. Considerin

Author

Liu, Hongrui (author);Hu, Binbin (author);Wang, Xiao (author);Shi, Chuan (author);Zhang, Zhiqiang (author);Zhou, Jun (author)

Publisher

ACM

Published

2022

Language

EN