ABSTRACT
Graph Neural Networks (GNN) are an effective technique for node classification, but their performance is easily affected by the quality of the primitive graph and the limited receptive field of message-passing. In this paper, we propose a new self-attention method, namely Chain of Propagation Prompting (CPP), to address the above issues as well as reduce dependence on label information when employing self-attention for node classification. To do this, we apply the self-attention framework to reduce the impact of a low-quality graph and to obtain a maximal receptive field for the message-passing. We also design a simple pattern of message-passing as the prompt to make self-attention capture complex patterns and reduce the dependence on label information. Comprehensive experimental results on real graph datasets demonstrate that CPP outperforms all relevant comparison methods.
- Shaked Brody, Uri Alon, and Eran Yahav. 2021. How attentive are graph attention networks? arXiv preprint arXiv:2105.14491 (2021).Google Scholar
- Deli Chen, Yankai Lin, Wei Li, Peng Li, Jie Zhou, and Xu Sun. 2020. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 3438--3445.Google ScholarCross Ref
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, Vol. 29 (2016).Google Scholar
- Frederik Diehl, Thomas Brunner, Michael Truong Le, and Alois Knoll. 2019. Graph neural networks for modelling traffic participant interaction. In 2019 IEEE Intelligent Vehicles Symposium (IV). IEEE, 695--701.Google ScholarDigital Library
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).Google Scholar
- Vijay Prakash Dwivedi and Xavier Bresson. 2020. A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699 (2020).Google Scholar
- Claudio Gallicchio and Alessio Micheli. 2020. Fast and deep graph neural networks. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 3898--3905.Google ScholarCross Ref
- Chen Gao, Xiang Wang, Xiangnan He, and Yong Li. 2022. Graph neural networks for recommender system. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 1623--1625.Google ScholarDigital Library
- Johannes Gasteiger, Aleksandar Bojchevski, and Stephan Günnemann. 2018. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997 (2018).Google Scholar
- Johannes Gasteiger, Stefan Weißenberger, and Stephan Günnemann. 2019. Diffusion improves graph learning. Advances in neural information processing systems, Vol. 32 (2019).Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017).Google Scholar
- Yang Hu, Haoxuan You, Zhecan Wang, Zhicheng Wang, Erjin Zhou, and Yue Gao. 2021. Graph-MLP: node classification without message passing in graph. arXiv preprint arXiv:2106.04051 (2021).Google Scholar
- Mingxuan Ju, Shifu Hou, Yujie Fan, Jianan Zhao, Yanfang Ye, and Liang Zhao. 2022. Adaptive Kernel Graph Neural Network. In 36th AAAI Conference on Artificial Intelligence (AAAI).Google Scholar
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Yaxin Li, Wei Jin, Han Xu, and Jiliang Tang. 2020. Deeprobust: A pytorch library for adversarial attacks and defenses. arXiv preprint arXiv:2005.06149 (2020).Google Scholar
- Meng Liu, Hongyang Gao, and Shuiwang Ji. 2020. Towards deeper graph neural networks. In SIGKDD. 338--348.Google Scholar
- Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys, Vol. 55, 9 (2023), 1--35.Google ScholarDigital Library
- Yao Ma, Xiaorui Liu, Neil Shah, and Jiliang Tang. 2021. Is homophily a necessity for graph neural networks? arXiv preprint arXiv:2106.06134 (2021).Google Scholar
- Erxue Min, Runfa Chen, Yatao Bian, Tingyang Xu, Kangfei Zhao, Wenbing Huang, Peilin Zhao, Junzhou Huang, Sophia Ananiadou, and Yu Rong. 2022. Transformer for graphs: An overview from architecture perspective. arXiv preprint arXiv:2202.08455 (2022).Google Scholar
- Aravind Sankar, Yanhong Wu, Liang Gou, Wei Zhang, and Hao Yang. 2018. Dynamic graph representation learning via self-attention networks. arXiv preprint arXiv:1812.09430 (2018).Google Scholar
- Aravind Sankar, Yanhong Wu, Liang Gou, Wei Zhang, and Hao Yang. 2020. Dysat: Deep neural representation learning on dynamic graphs via self-attention networks. In Proceedings of the 13th international conference on web search and data mining. 519--527.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, Vol. 29, 3 (2008), 93--93.Google Scholar
- Zhuoran Shen, Mingyuan Zhang, Haiyu Zhao, Shuai Yi, and Hongsheng Li. 2021b. Efficient attention: Attention with linear complexities. In CVPR. 3531--3539.Google Scholar
- Zi-Ang Shen, Tao Luo, Yuan-Ke Zhou, Han Yu, and Pu-Feng Du. 2021a. NPI-GNN: Predicting ncRNA--protein interactions with deep graph neural networks. Briefings in Bioinformatics , Vol. 22, 5 (2021), bbab051.Google ScholarCross Ref
- Susheel Suresh, Pan Li, Cong Hao, and Jennifer Neville. 2021. Adversarial graph augmentation to improve graph contrastive learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 15920--15933.Google Scholar
- Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017).Google Scholar
- Petar Velivčković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- Guangtao Wang, Rex Ying, Jing Huang, and Jure Leskovec. 2020. Multi-hop attention graph neural network. arXiv preprint arXiv:2009.14332 (2020).Google Scholar
- Guangtao Wang, Rex Ying, Jing Huang, and Jure Leskovec. 2021. Multi-hop Attention Graph Neural Networks. In IJCAI.Google Scholar
- Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, and Philip S Yu. 2019. Heterogeneous graph attention network. In The world wide web conference. 2022--2032.Google Scholar
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903 (2022).Google Scholar
- Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In International conference on machine learning. PMLR, 6861--6871.Google Scholar
- Louis-Pascal Xhonneux, Meng Qu, and Jian Tang. 2020. Continuous graph neural networks. In International Conference on Machine Learning. PMLR, 10432--10441.Google Scholar
- Sang Michael Xie, Aditi Raghunathan, Percy Liang, and Tengyu Ma. 2021. An explanation of in-context learning as implicit bayesian inference. arXiv preprint arXiv:2111.02080 (2021).Google Scholar
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).Google Scholar
- Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, and Jure Leskovec. 2021. QA-GNN: Reasoning with language models and knowledge graphs for question answering. arXiv preprint arXiv:2104.06378 (2021).Google Scholar
- Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation? Advances in Neural Information Processing Systems, Vol. 34 (2021), 28877--28888.Google Scholar
- Jiawei Zhang, Haopeng Zhang, Congying Xia, and Li Sun. 2020. Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140 (2020).Google Scholar
- Ke Zhang, Xinyan Pu, Jiaxing Li, Jiasong Wu, Huazhong Shu, and Youyong Kong. 2022. Hierarchical Diffusion Scattering Graph Neural Network. In IJCAI.Google Scholar
- Shichang Zhang, Yozen Liu, Yizhou Sun, and Neil Shah. 2021. Graph-less neural networks: Teaching old mlps new tricks via distillation. arXiv preprint arXiv:2110.08727 (2021).Google Scholar
- Jianan Zhao, Xiao Wang, Chuan Shi, Binbin Hu, Guojie Song, and Yanfang Ye. 2021. Heterogeneous graph structure learning for graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence. 4697--4705.Google ScholarCross Ref
- Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Olivier Bousquet, Quoc Le, and Ed Chi. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625 (2022).Google Scholar
- Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2020a. Graph neural networks: A review of methods and applications. AI Open, Vol. 1 (2020), 57--81.Google ScholarCross Ref
- Xianchen Zhou, Yaoyun Zeng, and Hongxia Wang. 2020b. RoGAT: a robust GNN combined revised GAT with adjusted graphs. arXiv preprint arXiv:2009.13038 (2020).Google Scholar
- Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. 2020. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in Neural Information Processing Systems, Vol. 33 (2020), 7793--7804.Google Scholar
- Yanqiao Zhu, Weizhi Xu, Jinghao Zhang, Qiang Liu, Shu Wu, and Liang Wang. 2021. Deep graph structure learning for robust representations: A survey. arXiv preprint arXiv:2103.03036, Vol. 14 (2021).Google Scholar
Index Terms
- Chain of Propagation Prompting for Node Classification
Recommendations
Multi-scale self-attention mixup for graph classification
Highlights- This paper proposes a novel Multi-scale self-attention mixup approach for graph classification.
- This paper innovatively introduces multi-scale graph representation for Mixup.
- A novel self-attention strategy is proposed to capture ...
Graphical abstractDisplay Omitted
AbstractData augmentation can effectively improve the generalization performance of neural networks. However, data augmentation for the graph domain is challenging due to the fact of irregular nature of the special non-Euclidean structure. In this paper, ...
Long-tailed graph neural networks via graph structure learning for node classification
AbstractLong-tailed methods have gained increasing attention and achieved excellent performance due to the long-tailed distribution in graphs, i.e., many small-degree tail nodes have limited structural connectivity. However, real-world graphs are ...
Task-Adaptive Few-shot Node Classification
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningNode classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of classes only consist of limited labeled nodes. Although Graph Neural ...
Comments