ABSTRACT
Graph data are pervasive in many real-world applications. Recently, increasing attention has been paid on graph neural networks (GNNs), which aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors with stackable network modules. Motivated by the observation that different nodes often require different iterations of aggregation to fully capture the structural information, in this paper, we propose to explicitly sample diverse iterations of aggregation for different nodes to boost the performance of GNNs. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. Moreover, it is not straightforward to derive an efficient algorithm since we need to feed the sampled nodes into different number of network layers. To address the above challenges, we propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process. Specifically, Policy-GNN uses a meta-policy to adaptively determine the number of aggregations for each node. The meta-policy is trained with deep reinforcement learning~(RL) by exploiting the feedback from the model. We further introduce parameter sharing and a buffer mechanism to boost the training efficiency. Experimental results on three real-world benchmark datasets suggest that Policy-GNN significantly outperforms the state-of-the-art alternatives, showing the promise in aggregation optimization for GNNs.
- Peter W Battaglia, Jessica B Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, et al. 2018. Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018).Google Scholar
- Xavier Bresson and Thomas Laurent. 2017. Residual gated graph convnets. arXiv preprint arXiv:1711.07553 (2017).Google Scholar
- Jie Chen, Tengfei Ma, and Cao Xiao. 2018. FastGCN: Fast learning with graph convolutional networks via importance sampling. In ICLR.Google Scholar
- Jie Chen, Tengfei Ma, and Cao Xiao. 2018. FastGCN: Fast learning with graph convolutional networks via importance sampling. In ICLRs.Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS.Google Scholar
- Matthias Fey and Jan E. Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds.Google Scholar
- Hongyang Gao and Shuiwang Ji. 2019. Graph u-nets. ICML (2019).Google Scholar
- Hongyang Gao, Zhengyang Wang, and Shuiwang Ji. 2018. Large-scale learnable graph convolutional networks. In KDD.Google Scholar
- Yang Gao, Hong Yang, Peng Zhang, Chuan Zhou, and Yue Hu. 2019. GraphNAS: Graph neural architecture search with reinforcement learning. arXiv preprint arXiv:1904.09981 (2019).Google Scholar
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In KDD.Google Scholar
- Nezihe Merve Gürel, Hansheng Ren, Yujing Wang, Hui Xue, Yaming Yang, and Ce Zhang. 2019. An anatomy of graph neural networks going deep via the lens of mutual information: exponential decay vs. full preservation. arXiv preprint arXiv:1910.04499 (2019).Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS.Google Scholar
- William L Hamilton, Rex Ying, and Jure Leskovec. 2017. Representation learning on graphs: Methods and applications. (2017).Google Scholar
- William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In NeurIPS.Google Scholar
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In WWW.Google Scholar
- Xia Hu, Lei Tang, Jiliang Tang, and Huan Liu. 2013. Exploiting social relations for sentiment analysis in microblogging. In WSDM.Google Scholar
- Wen-bing Huang, Tong Zhang, Yu Rong, and Junzhou Huang. 2018. Adaptive sampling towards fast graph representation learning. In NeurIPS.Google Scholar
- Xiao Huang, Qingquan Song, Yuening Li, and Xia Hu. 2019. Graph recurrent networks with attributed random walks. In KDD.Google Scholar
- Haifeng Jin, Qingquan Song, and Xia Hu. 2018. Auto-keras: Efficient neural architecture search with network morphism. arXiv preprint arXiv:1806.10282 (2018).Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR.Google Scholar
- Kwei-Herng Lai, Daochen Zha, Yuening Li, and Xia Hu. 2020. Dual policy distillation. arXiv preprint arXiv:2006.04061 (2020).Google Scholar
- Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradientbased learning applied to document recognition. IEEE (1998).Google Scholar
- Guohao Li, Matthias Müller, Ali K. Thabet, and Bernard Ghanem. 2019. Can GCNs go as deep as CNNs? arXiv preprint (2019).Google Scholar
- Yuening Li, Xiao Huang, Jundong Li, Mengnan Du, and Na Zou. 2019. SpecAE: Spectral autoencoder for anomaly Detection in Attributed Networks. In CIKM.Google Scholar
- Yuening Li, Daochen Zha, Praveen Venugopal, Na Zou, and Xia Hu. 2020. PyODDS: An end-to-end outlier detection system with automated machine learning. In WWW.Google Scholar
- Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Daniel Fink, Olivier Francon, Bala Raju, Hormoz Shahrzad, Arshak Navruzyan, Nigel Duffy, et al. 2019. Evolving deep neural networks. In Artificial Intelligence in the Age of Neural Networks and Brain Computing. Elsevier, 293--312.Google Scholar
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NeurIPS.Google Scholar
- Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin A. Riedmiller. 2013. Playing Atari with deep reinforcement Learning. arXiv preprint (2013).Google Scholar
- Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529.Google Scholar
- Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin A. Riedmiller, Andreas Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. Nature (2015).Google Scholar
- Kenta Oono and Taiji Suzuki. 2019. On asymptotic behaviors of graph cnns from dynamical systems perspective. arXiv preprint arXiv:1905.10947 (2019).Google Scholar
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. DeepWalk: online learning of social representations. In KDD.Google Scholar
- Hieu Pham, Melody Y Guan, Barret Zoph, Quoc V Le, and Jeff Dean. 2018. Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018).Google Scholar
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2009. The graph neural network model. IEEE Transactions on Neural Networks 20, 1 (2009), 61--80.Google ScholarDigital Library
- Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine (2008).Google Scholar
- Nino Shervashidze, Pascal Schweitzer, Erik Jan van Leeuwen, Kurt Mehlhorn, and Karsten M. Borgwardt. 2011. Weisfeiler-Lehman Graph Kernels. JMLR (2011).Google ScholarDigital Library
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In ICLR.Google Scholar
- Christopher John Cornish Hellaby Watkins. 1989. Learning from delayed rewards. Ph.D. Dissertation. King's College.Google Scholar
- Zhongwen Xu, Hado van Hasselt, and David Silver. 2018. Meta-gradient reinforcement learning. In NeurIPS.Google Scholar
- Jiaxuan You, Bowen Liu, Zhitao Ying, Vijay Pande, and Jure Leskovec. 2018. Graph convolutional policy network for goal-directed molecular graph generation. In NeurIPS.Google Scholar
- Jiaxuan You, Rex Ying, Xiang Ren, William L Hamilton, and Jure Leskovec. 2018. Graphrnn: Generating realistic graphs with deep auto-regressive models. arXiv preprint arXiv:1802.08773 (2018).Google Scholar
- Daochen Zha, Kwei-Herng Lai, Yuanpu Cao, Songyi Huang, Ruzhe Wei, Junyu Guo, and Xia Hu. 2019. RLCard: A toolkit for reinforcement learning in card games. arXiv preprint arXiv:1910.04376 (2019).Google Scholar
- Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, and Xia Hu. 2019. Experience replay optimization. IJCAI.Google Scholar
- Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2018. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434 (2018).Google Scholar
- Kaixiong Zhou, Qingquan Song, Xiao Huang, and Xia Hu. 2019. Auto-GNN: Neural architecture search of graph neural networks. arXiv preprint arXiv:1909.03184 (2019).Google Scholar
- Kaixiong Zhou, Qingquan Song, Xiao Huang, Daochen Zha, Na Zou, and Xia Hu. 2019. Multi-Channel graph convolutional networks. arXiv preprint arXiv:1912.08306 (2019).Google Scholar
- Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016).Google Scholar
Index Terms
- Policy-GNN: Aggregation Optimization for Graph Neural Networks
Recommendations
Similarity-navigated graph neural networks for node classification
AbstractGraph Neural Networks are effective in learning representations of graph-structured data. Some recent works are devoted to addressing heterophily, which exists ubiquitously in real-world networks, breaking the homophily assumption that nodes ...
Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case
AbstractDeep Reinforcement Learning (DRL) has shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficiently solve many relevant optimization problems (e.g., ...
Generating a Graph Colouring Heuristic with Deep Q-Learning and Graph Neural Networks
Learning and Intelligent OptimizationAbstractThe graph colouring problem consists of assigning labels, or colours, to the vertices of a graph such that no two adjacent vertices share the same colour. In this work we investigate whether deep reinforcement learning can be used to discover a ...
Comments