Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However, these algorithms struggle to learn policy distributions that are proportional to rewards and have limited exploration capabilities. In this paper, we innovatively formulate the graph active learning problem as a generative process, named GFlowGNN, which generates various samples through sequential actions with probabilities precisely proportional to a predefined reward function. Furthermore, we propose the concept of flow nodes and flow features to efficiently model graphs as flows based on generative flow networks, where the policy network is trained with specially designed rewards. Extensive experiments on real datasets show that the proposed approach has good exploration capability and transferability, outperforming various state-of-the-art methods.

[1]  Jianye Hao,et al.  DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks , 2023, ICLR.

[2]  Jianye Hao,et al.  CFlowNets: Continuous Control with Generative Flow Networks , 2023, ICLR.

[3]  Y. Bengio,et al.  Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes , 2022, ArXiv.

[4]  Wentao Zhang,et al.  Information Gain Propagation: a new way to Graph Active Learning with Soft Labels , 2022, ICLR.

[5]  Bonaventure F. P. Dossou,et al.  Biological Sequence Design with GFlowNets , 2022, ICML.

[6]  Aaron C. Courville,et al.  Generative Flow Networks for Discrete Probabilistic Modeling , 2022, ICML.

[7]  Ye Yuan,et al.  Deep Unsupervised Active Learning on Learnable Graphs , 2021, IEEE transactions on neural networks and learning systems.

[8]  Zhi Yang,et al.  RIM: Reliable Influence-based Active Learning on Graphs , 2021, NeurIPS.

[9]  Doina Precup,et al.  Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation , 2021, NeurIPS.

[10]  Ling Chen,et al.  SEAL: Semisupervised Adversarial Active Learning on Attributed Graphs , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Jian Wu,et al.  Multi-Label Active Learning Algorithms for Image Classification , 2020, ACM Comput. Surv..

[12]  Matthew Stewart,et al.  IEEE Transactions on Cybernetics , 2015, IEEE Transactions on Cybernetics.

[13]  Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining , 2021 .

[14]  Enhong Chen,et al.  ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction , 2020, KDD.

[15]  Yizhou Sun,et al.  GPT-GNN: Generative Pre-Training of Graph Neural Networks , 2020, KDD.

[16]  L. Akoglu,et al.  Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs , 2020, NeurIPS.

[17]  Marc-Alexandre Côté,et al.  Graph Policy Network for Transferable Active Learning on Graphs , 2020, NeurIPS.

[18]  Tomasz Malisiewicz,et al.  SuperGlue: Learning Feature Matching With Graph Neural Networks , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[20]  Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , 2020 .

[21]  Jiawei Jiang,et al.  Snapshot boosting: a fast ensemble framework for deep neural networks , 2019, Science China Information Sciences.

[22]  Hanghang Tong,et al.  Graph convolutional networks: a comprehensive review , 2019, Computational Social Networks.

[23]  Xiangliang Zhang,et al.  ActiveHNE: Active Heterogeneous Network Embedding , 2019, IJCAI.

[24]  J. Leskovec,et al.  GNNExplainer: Generating Explanations for Graph Neural Networks , 2019, NeurIPS.

[25]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Hong Yang,et al.  Active Discriminative Network Representation Learning , 2018, IJCAI.

[27]  Brian Mac Namee,et al.  IEEE Transactions on Neural Networks and Learning Systems Information for Authors , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[29]  Wei Liu,et al.  Exploring Representativeness and Informativeness for Active Learning , 2019, IEEE Transactions on Cybernetics.

[30]  Kevin Chen-Chuan Chang,et al.  Active Learning for Graph Embedding , 2017, ArXiv.

[31]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[32]  Yi Yang,et al.  Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization , 2015, International Journal of Computer Vision.

[33]  Robert L. Grossman,et al.  Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining , 2013, KDD 2013.

[34]  Tianshun Yao,et al.  Active Learning with Sampling by Uncertainty and Density for Word Sense Disambiguation and Text Classification , 2008, COLING.

[35]  Ross D. King,et al.  Active Learning for Regression Based on Query by Committee , 2007, IDEAL.

[36]  Carla E. Brodley,et al.  Proceedings of the twenty-first international conference on Machine learning , 2004, International Conference on Machine Learning.

[37]  Pierre Isabelle,et al.  Proceedings of the 40th Annual Meeting on Association for Computational Linguistics , 2002, ACL 2002.

[38]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .