Transfer Active Learning For Graph Neural Networks

Shengding Hu, Meng Qu, Zhiyuan Liu, Jian Tang

TL;DR: We propose a novel method to learn a transferable active learning policy for Graph Neural Networks via reinforcement learning and policy distillation.

Abstract: Graph neural networks have been proved very effective for a variety of prediction tasks on graphs such as node classification. Generally, a large number of labeled data are required to train these networks. However, in reality it could be very expensive to obtain a large number of labeled data on large-scale graphs. In this paper, we studied active learning for graph neural networks, i.e., how to effectively label the nodes on a graph for training graph neural networks. We formulated the problem as a sequential decision process, which sequentially label informative nodes, and trained a policy network to maximize the performance of graph neural networks for a specific task. Moreover, we also studied how to learn a universal policy for labeling nodes on graphs with multiple training graphs and then transfer the learned policy to unseen graphs. Experimental results on both settings of a single graph and multiple training graphs (transfer learning setting) prove the effectiveness of our proposed approaches over many competitive baselines.

Code: https://drive.google.com/drive/folders/1GFGR2WFEuG49MQN-nX4pkZj9Y_E7vPP5

Keywords: Active Learning, Graph Neural Networks, Transfer Learning, Reinforcement Learning