research-article

Model-Agnostic Augmentation for Accurate Graph Classification

Authors:

U KangAuthors Info & Claims

WWW '22: Proceedings of the ACM Web Conference 2022

Pages 1281 - 1291

https://doi.org/10.1145/3485447.3512175

Published: 25 April 2022 Publication History

Abstract

Given a graph dataset, how can we augment it for accurate graph classification? Graph augmentation is an essential strategy to improve the performance of graph-based tasks, and has been widely utilized for analyzing web and social graphs. However, previous works for graph augmentation either a) involve the target model in the process of augmentation, losing the generalizability to other tasks, or b) rely on simple heuristics that lead to unreliable results. In this work, we introduce five desired properties for effective augmentation. Then, we propose NodeSam (Node Split and Merge) and SubMix (Subgraph Mix), two model-agnostic algorithms for graph augmentation that satisfy all desired properties with different motivations. NodeSam makes a balanced change of the graph structure to minimize the risk of semantic change, while SubMix mixes random subgraphs of multiple graphs to create rich soft labels combining the evidence for different classes. Our experiments on social networks and molecular graphs show that NodeSam and SubMix outperform existing approaches in graph classification.

References

[1]

Filippo Maria Bianchi, Daniele Grattarola, and Cesare Alippi. 2020. Spectral Clustering with Graph Neural Networks for Graph Pooling. In ICML.

[2]

Ronald V. Book. 1974. Comparing Complexity Classes. J. Comput. Syst. Sci. 9, 2 (1974), 213–229. https://doi.org/10.1016/S0022-0000(74)80008-5

Digital Library

[3]

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 AAAI.

[4]

Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. 2018. Adversarial Attack on Graph Structured Data. In ICML.

[5]

Terrance Devries and Graham W. Taylor. 2017. Improved Regularization of Convolutional Neural Networks with Cutout. CoRR abs/1708.04552(2017). arxiv:1708.04552

[6]

Boxin Du and Hanghang Tong. 2019. MrMine: Multi-resolution Multi-network Embedding. In CIKM.

[7]

Fuli Feng, Xiangnan He, Jie Tang, and Tat-Seng Chua. 2019. Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure. CoRR abs/1902.08226(2019). arxiv:1902.08226

[8]

Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard H. Hovy. 2021. A Survey of Data Augmentation Approaches for NLP. In Findings of ACL.

[9]

Maayan Frid-Adar, Idit Diamant, Eyal Klang, Michal Amitai, Jacob Goldberger, and Hayit Greenspan. 2018. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing 321(2018), 321–331.

[10]

Kun Fu, Tingyun Mao, Yang Wang, Daoyu Lin, Yuanben Zhang, Junjian Zhan, Xian Sun, and Feng Li. 2021. TS-Extractor: large graph exploration via subgraph extraction based on topological and semantic information. J. Vis. 24, 1 (2021), 173–190.

Digital Library

[11]

Adrian Galdran, Aitor Alvarez-Gila, Maria Inês Meyer, Cristina López Saratxaga, Teresa Araujo, Estíbaliz Garrote, Guilherme Aresta, Pedro Costa, Ana Maria Mendonça, and Aurélio J. C. Campilho. 2017. Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis. CoRR abs/1703.03702(2017). arxiv:1703.03702

[12]

Saehan Jo, Jaemin Yoo, and U Kang. 2018. Fast and Scalable Distributed Loopy Belief Propagation on Real-World Graphs. In WSDM.

[13]

Jinhong Jung, Jaemin Yoo, and U Kang. 2020. Signed Graph Diffusion Network. CoRR abs/2012.14191(2020). arXiv:2012.14191

[14]

Jang-Hyun Kim, Wonho Choo, and Hyun Oh Song. 2020. Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup. In ICML.

[15]

Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR.

[16]

Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.

[17]

Johannes Klicpera, Stefan Weißenberger, and Stephan Günnemann. 2019. Diffusion Improves Graph Learning. In NeurIPS.

[18]

Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu, Chen Zhu, Bernard Ghanem, Gavin Taylor, and Tom Goldstein. 2020. FLAG: Adversarial Data Augmentation for Graph Neural Networks. CoRR abs/2010.09891(2020). arxiv:2010.09891

[19]

Jin-Ha Lee, Muhammad Zaigham Zaheer, Marcella Astrid, and Seung-Ik Lee. 2020. SmoothMix: a Simple Yet Effective Data Augmentation to Train Robust Classifiers. In CVPR.

[20]

Jiaqi Ma, Shuangrui Ding, and Qiaozhu Mei. 2020. Towards More Practical Adversarial Attacks on Graph Neural Networks. In NeurIPS.

[21]

Yao Ma, Suhang Wang, Charu C. Aggarwal, and Jiliang Tang. 2019. Graph Convolutional Networks with EigenPooling. In KDD.

[22]

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard. 2016. DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks. In CVPR.

[23]

Christopher Morris, Nils M. Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann. 2020. TUDataset: A collection of benchmark datasets for learning with graphs. CoRR abs/2007.08663(2020). arxiv:2007.08663

[24]

Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu, and Santhoshkumar Saminathan. 2016. subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs. CoRR abs/1606.08928(2016). arxiv:1606.08928

[25]

Shirui Pan, Jia Wu, and Xingquan Zhu. 2015. CogBoost: Boosting for Fast Cost-Sensitive Graph Classification. IEEE Trans. Knowl. Data Eng. 27, 11 (2015), 2933–2946. https://doi.org/10.1109/TKDE.2015.2391115

Digital Library

[26]

Bastian Rieck, Christian Bock, and Karsten M. Borgwardt. 2019. A Persistent Weisfeiler-Lehman Procedure for Graph Classification. In ICML.

[27]

Ignacio Rocco, Relja Arandjelovic, and Josef Sivic. 2019. Convolutional Neural Network Architecture for Geometric Matching. IEEE Trans. Pattern Anal. Mach. Intell. 41, 11 (2019).

[28]

Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2020. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. In ICLR.

[29]

Nino Shervashidze, Pascal Schweitzer, Erik Jan van Leeuwen, Kurt Mehlhorn, and Karsten M. Borgwardt. 2011. Weisfeiler-Lehman Graph Kernels. J. Mach. Learn. Res. 12(2011).

[30]

Connor Shorten and Taghi M. Khoshgoftaar. 2019. A survey on Image Data Augmentation for Deep Learning. J. Big Data 6(2019), 60.

[31]

Krishna Kumar Singh and Yong Jae Lee. 2017. Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization. In ICCV.

[32]

Ryo Takahashi, Takashi Matsubara, and Kuniaki Uehara. 2020. Data Augmentation Using Random Image Cropping and Patching for Deep CNNs. IEEE Trans. Circuits Syst. Video Technol. 30, 9 (2020).

Digital Library

[33]

Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008).

[34]

Vikas Verma, Meng Qu, Alex Lamb, Yoshua Bengio, Juho Kannala, and Jian Tang. 2019. GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning. CoRR abs/1909.11715(2019). arxiv:1909.11715

[35]

Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, and Bryan Hooi. 2020. GraphCrop: Subgraph Cropping for Graph Classification. CoRR abs/2009.10564(2020). arxiv:2009.10564

[36]

Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, and Bryan Hooi. 2021. CurGraph: Curriculum Learning for Graph Classification. In WWW.

[37]

Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, and Bryan Hooi. 2021. Mixup for Node and Graph Classification. In WWW.

[38]

Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, Juncheng Liu, and Bryan Hooi. 2020. NodeAug: Semi-Supervised Node Classification with Data Augmentation. In KDD.

[39]

Qingsong Wen, Liang Sun, Fan Yang, Xiaomin Song, Jingkun Gao, Xue Wang, and Huan Xu. 2021. Time Series Data Augmentation for Deep Learning: A Survey. In IJCAI.

[40]

Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, and Xue Lin. 2019. Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. In IJCAI.

[41]

Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR.

[42]

Pinar Yanardag and S. V. N. Vishwanathan. 2015. Deep Graph Kernels. In KDD.

[43]

Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L. Hamilton, and Jure Leskovec. 2018. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. In KDD.

[44]

Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, and Jure Leskovec. 2018. Hierarchical Graph Representation Learning with Differentiable Pooling. In NeurIPS.

[45]

Jaemin Yoo, Hyunsik Jeon, and U Kang. 2019. Belief Propagation Network for Hard Inductive Semi-Supervised Learning. In IJCAI.

[46]

Jaemin Yoo, U Kang, Mauro Scanagatta, Giorgio Corani, and Marco Zaffalon. 2020. Sampling Subgraphs with Guaranteed Treewidth for Accurate and Efficient Graphical Inference. In WSDM.

[47]

Jaemin Yoo, Junghun Kim, Hoyoung Yoon, Geonsoo Kim, Changwon Jang, and U Kang. 2021. Accurate Graph-Based PU Learning without Class Prior. In ICDM.

[48]

Yuning You, Tianlong Chen, Yang Shen, and Zhangyang Wang. 2021. Graph Contrastive Learning Automated. In ICML.

[49]

Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph Contrastive Learning with Augmentations. In NeurIPS.

[50]

Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Seong Joon Oh, Youngjoon Yoo, and Junsuk Choe. 2019. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features. In ICCV.

[51]

Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor K. Prasanna. 2020. GraphSAINT: Graph Sampling Based Inductive Learning Method. In ICLR.

[52]

Hongyi Zhang, Moustapha Cissé, Yann N. Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In ICLR.

[53]

Tong Zhao, Yozen Liu, Leonardo Neves, Oliver J. Woodford, Meng Jiang, and Neil Shah. 2020. Data Augmentation for Graph Neural Networks. CoRR abs/2006.06830(2020). arxiv:2006.06830

[54]

Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, and Yi Yang. 2020. Random Erasing Data Augmentation. In AAAI.

[55]

Jiajun Zhou, Jie Shen, and Qi Xuan. 2020. Data Augmentation for Graph Classification. In CIKM.

[56]

Xinyue Zhu, Yifan Liu, Jiahong Li, Tao Wan, and Zengchang Qin. 2018. Emotion Classification with Data Augmentation Using Generative Adversarial Networks. In PAKDD.

[57]

Daniel Zügner and Stephan Günnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In ICLR.

Cited By

Jiang TWang ZYu WWang JYu SBao XWei BXuan Q(2024)Mix-Key: graph mixup with key structures for molecular property predictionBriefings in Bioinformatics10.1093/bib/bbae16525:3Online publication date: 5-May-2024
https://doi.org/10.1093/bib/bbae165
Ling HJiang ZLiu MJi SZou NKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Graph mixup with soft alignmentsProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619287(21335-21349)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619287
Ma GHu CGe LZhang HElkind E(2023)Multi-view robust graph representation learning for graph classificationProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/449(4037-4045)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/449

Index Terms

Model-Agnostic Augmentation for Accurate Graph Classification

Index terms have been assigned to the content through auto-classification.

Recommendations

Mixup for Node and Graph Classification
WWW '21: Proceedings of the Web Conference 2021

Mixup is an advanced data augmentation method for training neural network based image classifiers, which interpolates both features and labels of a pair of images to produce synthetic samples. However, devising the Mixup methods for graph learning is ...
Data Augmentation for Graph Classification
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge Management

Graph classification, which aims to identify the category labels of graphs, plays a significant role in drug classification, toxicity detection, protein analysis etc. However, the limitation of scale of benchmark datasets makes it easy for graph ...
Understanding the roles of sub-graph features for graph classification: an empirical study perspective
CIKM '13: Proceedings of the 22nd ACM international conference on Information & Knowledge Management

Graph classification concerns the learning of discriminative models, from structured training data, to classify previously unseen graph samples into specific categories, where the main challenge is to explore structural information in the training data ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

WWW '22: Proceedings of the ACM Web Conference 2022

April 2022

3764 pages

ISBN:9781450390965

DOI:10.1145/3485447

Editors:
Frédérique Laforest
INSA Lyon, France
,
Raphaël Troncy
EURECOM, France
,
Elena Simperl
King’s College London, UK
,
Deepak Agarwal
Pinterest, USA
,
Aristides Gionis
KTH Royal Institute of Technology, Sweden
,
Ivan Herman
W3C / retired
,
Lionel Médini
Université Lyon 1, France

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 April 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

WWW '22

Sponsor:

SIGWEB

WWW '22: The ACM Web Conference 2022

April 25 - 29, 2022

Virtual Event, Lyon, France

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
360
Total Downloads

Downloads (Last 12 months)99
Downloads (Last 6 weeks)4

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Jiang TWang ZYu WWang JYu SBao XWei BXuan Q(2024)Mix-Key: graph mixup with key structures for molecular property predictionBriefings in Bioinformatics10.1093/bib/bbae16525:3Online publication date: 5-May-2024
https://doi.org/10.1093/bib/bbae165
Ling HJiang ZLiu MJi SZou NKrause ABrunskill ECho KEngelhardt BSabato SScarlett J(2023)Graph mixup with soft alignmentsProceedings of the 40th International Conference on Machine Learning10.5555/3618408.3619287(21335-21349)Online publication date: 23-Jul-2023
https://dl.acm.org/doi/10.5555/3618408.3619287
Ma GHu CGe LZhang HElkind E(2023)Multi-view robust graph representation learning for graph classificationProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/449(4037-4045)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/449

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents