Semi-supervised Node Classification with Imbalanced Receptive Field

Wentao Zhang, Xinyi Gao, Ling Yang, Meng Cao, Ping Huang, Jiulong Shan, Hongzhi Yin, Bin CUI

Keywords: Graph Neural Network, Imbalanced Node Classification, Influence Maximization, Influence Balance

TL;DR: The first attempt to consider the influence imbalance issue in semi-supervised node classification task of GNNs.

Abstract: The imbalanced data classification problem has aroused lots of concerns from both academia and industrial since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem, and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experiments on four public datasets demonstrate the effectiveness of our method in relieving influence-imbalance issue. For example, when training a GCN with the imbalance ratio of 0.1, BIM significantly outperforms the state-of-the-art baseline ReNode by 8.9\%-13.5\% in four public datasets in terms of the F1 score.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning