# Class-Balanced and Reinforced Active Learning on Graphs

arXiv: https://arxiv.org/abs/2402.10074 · HTML: https://mlsanity.com/paper/2402.10074/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios](https://mlsanity.com/paper/2107.00717/) (2021)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Topology-Imbalance Learning for Semi-Supervised Node Classification](https://mlsanity.com/paper/2110.04099/) (2021)
- [Active Learning for Graph Embedding](https://mlsanity.com/paper/1705.05085/) (2017)
- [Graph Policy Network for Transferable Active Learning on Graphs](https://mlsanity.com/paper/2006.13463/) (2020)
- [TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2206.12917/) (2022)
- [Active Learning for Graph Neural Networks via Node Feature Propagation](https://mlsanity.com/paper/1910.07567/) (2019)
- [GALAXY: Graph-based Active Learning at the Extreme](https://mlsanity.com/paper/2202.01402/) (2022)
- [Class-Imbalanced Learning on Graphs: A Survey](https://mlsanity.com/paper/2304.04300/) (2023)
- [Network Embedding with Completely-imbalanced Labels](https://mlsanity.com/paper/2007.03545/) (2020)
- [GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification](https://mlsanity.com/paper/2302.12814/) (2023)
- [Algorithm Selection for Deep Active Learning with Imbalanced Datasets](https://mlsanity.com/paper/2302.07317/) (2023)
- [ActiveHNE: Active Heterogeneous Network Embedding](https://mlsanity.com/paper/1905.05659/) (2019)
- [Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection](https://mlsanity.com/paper/2302.06900/) (2023)

## Built on by (most cited first, 1 of 1)

- [DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation](https://mlsanity.com/paper/2409.08946/) (2024)

## Abstract (arXiv)

Graph neural networks (GNNs) have demonstrated significant success in various applications, such as node classification, link prediction, and graph classification. Active learning for GNNs aims to query the valuable samples from the unlabeled data for annotation to maximize the GNNs' performance at a lower cost. However, most existing algorithms for reinforced active learning in GNNs may lead to a highly imbalanced class distribution, especially in highly skewed class scenarios. GNNs trained with class-imbalanced labeled data are susceptible to bias toward majority classes, and the lower performance of minority classes may lead to a decline in overall performance. To tackle this issue, we propose a novel class-balanced and reinforced active learning framework for GNNs, namely, GCBR. It learns an optimal policy to acquire class-balanced and informative nodes for annotation, maximizing the performance of GNNs trained with selected labeled nodes. GCBR designs class-balance-aware states, as well as a reward function that achieves trade-off between model performance and class balance. The reinforcement learning algorithm Advantage Actor-Critic (A2C) is employed to learn an optimal policy stably and efficiently. We further upgrade GCBR to GCBR++ by introducing a punishment mechanism to obtain a more class-balanced labeled set. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed approaches, achieving superior performance over state-of-the-art baselines.