Class-Balanced and fast active learning for graph neural networks via reinforcement learning

Graph neural networks (GNNs) have recently demonstrated significant success. Active learning for GNNs aims to query the valuable samples from the unlabeled data for annotation to maximize the GNNs’ performance at a low cost. However, most existing methods for reinforced active learning in GNNs may lead to a highly imbalanced class distribution, especially in highly skewed class scenarios. This further adversely affects the classification performance. To tackle this issue, in this paper, we propose a novel reinforced Class-Balanced Active Learning framework for GNNs, namely, GraphCBAL. It learns an optimal policy to acquire class-balanced and informative nodes for annotation, maximizing the performance of GNNs trained with selected labeled nodes. GraphCBAL designs class-balance-aware states, as well as a reward function that achieves a trade-off between model performance and class balance. We further upgrade GraphCBAL to GraphCBAL++ by introducing a punishment mechanism to obtain a more class-balanced labeled set. To improve the efficiency of GraphCBAL, we propose BGraphCBAL, a batch-mode extension that selects multiple nodes for labeling at each iteration. We formulate batch active learning as a cooperative multi-agent reinforcement learning problem. We further design a multi-agent policy network that not only accounts for the informativeness and class balance of candidate nodes, but also models interactions among nodes selected within the same batch. Extensive experiments on multiple datasets demonstrate the effectiveness and efficiency of the proposed approaches, achieving superior performance over state-of-the-art baselines. In particular, our methods can strike a balance between classification results and class balance. We provide our code and data at https://github.com/cici-chengcheng/GraphCBAL.