skip to main content
10.1145/3503161.3548012acmconferencesArticle/Chapter ViewAbstractPublication PagesmmConference Proceedingsconference-collections
research-article

DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification

Published: 10 October 2022 Publication History

Abstract

Graph neural networks (GNNs) have achieved state-of-the-art results on graph classification tasks. They have been primarily studied in cases of supervised end-to-end training, which requires abundant task-specific labels. Unfortunately, annotating labels of graph data could be prohibitively expensive or even impossible in many applications. An effective solution is to incorporate labeled graphs from a different, but related source domain, to develop a graph classification model for the target domain. However, the problem of unsupervised domain adaptation for graph classification is challenging due to potential domain discrepancy in graph space as well as the label scarcity in the target domain. In this paper, we present a novel GNN framework named DEAL by incorporating both source graphs and target graphs, which is featured by two modules, i.e., adversarial perturbation and pseudo-label distilling. Specifically, to overcome domain discrepancy, we equip source graphs with target semantics by applying to them adaptive perturbations which are adversarially trained against a domain discriminator. Additionally, DEAL explores distinct feature spaces at different layers of the GNN encoder, which emphasize global and local semantics respectively. Then, we distill the consistent predictions from two spaces to generate reliable pseudo-labels for sufficiently utilizing unlabeled data, which further improves the performance of graph classification. Extensive experiments on a wide range of graph classification datasets reveal the effectiveness of our proposed DEAL.

Supplementary Material

MP4 File (????.mp4)
Presentation video

References

[1]
Jinheon Baek, Minki Kang, and Sung Ju Hwang. 2021. Accurate Learning of Graph Representations with Graph Multiset Pooling. In Proceedings of the International Conference on Learning Representations.
[2]
Axel D Becke. 2014. Perspective: Fifty years of density-functional theory in chemical physics. The Journal of Chemical Physics 140, 18 (2014), 18A301.
[3]
Cristian Bodnar, Fabrizio Frasca, Nina Otter, Yu GuangWang, Pietro Liò, Guido F Montufar, and Michael Bronstein. 2021. Weisfeiler and lehman go cellular: Cw networks. In Proceedings of the Conference on Neural Information Processing Systems. 2625--2640.
[4]
Karsten M Borgwardt and Hans-Peter Kriegel. 2005. Shortest-path kernels on graphs. 74--81.
[5]
Minghao Chen, Hongyang Xue, and Deng Cai. 2019. Domain adaptation for semantic segmentation with maximum squares loss. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2090--2099.
[6]
Weilin Cong, Morteza Ramezani, and Mehrdad Mahdavi. 2021. On provable benefits of depth in training graph convolutional networks. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 34. 9936--9949.
[7]
Jindou Dai, Yuwei Wu, Zhi Gao, and Yunde Jia. 2021. A hyperbolic-to-hyperbolic graph convolutional network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 154--163.
[8]
Wanxia Deng, Yawen Cui, Zhen Liu, Gangyao Kuang, Dewen Hu, Matti Pietikäinen, and Li Liu. 2021. Informative Class-Conditioned Feature Alignment for Unsupervised Domain Adaptation. In Proceedings of the ACM International Conference on Multimedia. 1303--1312.
[9]
Ming Ding, Jie Tang, and Jie Zhang. 2018. Semi-supervised learning on graphs with generative adversarial nets. In International Conference on Information and Knowledge Management. 913--922.
[10]
Paul D Dobson and Andrew J Doig. 2003. Distinguishing enzyme structures from non-enzymes without alignments. Journal of molecular biology 330, 4 (2003), 771--783.
[11]
Jeff Donahue, Philipp Krähenbühl, and Trevor Darrell. 2016. Adversarial feature learning. arXiv preprint arXiv:1605.09782 abs/1605.09782 (2016).
[12]
Shaohua Fan, Xiao Wang, Chuan Shi, Peng Cui, and Bai Wang. 2021. Generalizing Graph Neural Networks on Out-Of-Distribution Graphs. arXiv preprint arXiv:2111.10657 (2021).
[13]
Fuli Feng, Xiangnan He, Jie Tang, and Tat-Seng Chua. 2019. Graph adversarial training: Dynamically regularizing based on graph structure. IEEE Transactions on Knowledge and Data Engineering 33, 6 (2019), 2493--2504.
[14]
Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In Proceedings of ICLR Workshop on Representation Learning on Graphs and Manifolds.
[15]
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. Journal of Machine Learning Research 17, 1 (2016), 2096--2030.
[16]
Hongchang Gao, Jian Pei, and Heng Huang. 2019. Progan: Network embedding via proximity generative adversarial network. In Proceedings of the International ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1308--1316.
[17]
Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In Proceedings of the International Conference on Machine Learning. 1263--1272.
[18]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Conference on Neural Information Processing Systems.
[19]
Zhongkai Hao, Chengqiang Lu, Zhenya Huang, Hao Wang, Zheyuan Hu, Qi Liu, Enhong Chen, and Cheekong Lee. 2020. ASGN: An active semi-supervised graph neural network for molecular property prediction. In Proceedings of the International ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 731--752.
[20]
Tao He, Leqi Shen, Yuchen Guo, Guiguang Ding, and Zhenhua Guo. 2022. SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 879--887.
[21]
Bingyu Hu, Zheng-Jun Zha, Jiawei Liu, Xierong Zhu, and Hongtao Xie. 2021. Cluster and Scatter: A Multi-grained Active Semi-supervised Learning Framework for Scalable Person Re-identification. In Proceedings of the ACM International Conference on Multimedia. 2605--2614.
[22]
Qianjiang Hu, XiaoWang,Wei Hu, and Guo-Jun Qi. 2021. AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1074--1083.
[23]
Jeroen Kazius, Ross McGuire, and Roberta Bursi. 2005. Derivation and validation of toxicophores for mutagenicity prediction. Journal of medicinal chemistry 48, 1 (2005), 312--320.
[24]
Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations.
[25]
Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of the International Conference on Learning Representations.
[26]
Ryosuke Kojima, Shoichi Ishida, Masateru Ohta, Hiroaki Iwata, Teruki Honma, and Yasushi Okuno. 2020. kGCN: a graph-based deep learning framework for chemical structures. Journal of Cheminformatics 12 (2020), 1--10.
[27]
Chen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, and Daniel Ulbricht. 2019. Sliced wasserstein discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10285--10295.
[28]
Dong-Hyun Lee et al. 2013. Pseudo-label: The simple and efficient semisupervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML. 896.
[29]
Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-attention graph pooling. In Proceedings of the International Conference on Machine Learning. 3734--3743.
[30]
Shuang Li, Mixue Xie, Kaixiong Gong, Chi Harold Liu, Yulin Wang, and Wei Li. 2021. Transferable semantic augmentation for domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11516--11525.
[31]
Yujia Li, Richard Zemel, Marc Brockschmidt, and Daniel Tarlow. 2016. Gated Graph Sequence Neural Networks. In Proceedings of the International Conference on Learning Representations.
[32]
Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In Proceedings of the International Conference on Machine Learning. 6028--6039.
[33]
Changshu Liu, Liangjian Wen, Zhao Kang, Guangchun Luo, and Ling Tian. 2021. Self-supervised consensus representation learning for attributed graph. In Proceedings of the ACM International Conference on Multimedia. 2654--2662.
[34]
Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. 2018. Conditional adversarial domain adaptation. Proceedings of the Conference on Neural Information Processing Systems, 1647--1657.
[35]
Ning Ma, Jiajun Bu, Jieyu Yang, Zhen Zhang, Chengwei Yao, Zhi Yu, Sheng Zhou, and Xifeng Yan. 2020. Adaptive-step graph meta-learner for few-shot graph classification. In International Conference on Information and Knowledge Management. 1055--1064.
[36]
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. In ICML Workshop.
[37]
Francesco Orsini, Paolo Frasconi, and Luc De Raedt. 2015. Graph invariant kernels. In International Joint Conference on Artificial Intelligence. 3756--3762.
[38]
Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017).
[39]
Zhihao Peng, Hui Liu, Yuheng Jia, and Junhui Hou. 2021. Attention-driven Graph Clustering Network. In Proceedings of the ACM International Conference on Multimedia. 935--943.
[40]
Kuniaki Saito, Kohei Watanabe, Yoshitaka Ushiku, and Tatsuya Harada. 2018. Maximum classifier discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3723--3732.
[41]
Erich Schubert, Jörg Sander, Martin Ester, Hans Peter Kriegel, and Xiaowei Xu. [n.d.]. DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Transactions on Database Systems 42, 3 ([n. d.]), 1--21.
[42]
Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M Borgwardt. 2011. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research 12, 9 (2011), 2539--2561.
[43]
Fan-Yun Sun, Jordan Hoffmann, Vikas Verma, and Jian Tang. 2020. Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In Proceedings of the International Conference on Learning Representations.
[44]
Susheel Suresh, Pan Li, Cong Hao, and Jennifer Neville. 2021. Adversarial graph augmentation to improve graph contrastive learning. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 34.
[45]
Jeffrey J Sutherland, Lee A O'brien, and Donald FWeaver. 2003. Spline-fitting with a genetic algorithm: A method for developing classification structure- activity relationships. Journal of Chemical Information and Computer Sciences (2003).
[46]
Jesper E Van Engelen and Holger H Hoos. 2020. A survey on semi-supervised learning. Machine Learning 109, 2 (2020), 373--440.
[47]
Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. In Proceedings of the International Conference on Learning Representations.
[48]
Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018. Graphgan: Graph representation learning with generative adversarial nets. In Proceedings of the AAAI Conference on Artificial Intelligence. 2508--2515.
[49]
JiayuWang,Wengang Zhou, Guo-Jun Qi, Zhongqian Fu, Qi Tian, and Houqiang Li. 2020. Transformation gan for unsupervised image synthesis and representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 469--478.
[50]
LeiWang, Yuchun Huang, Yaolin Hou, Shenman Zhang, and Jie Shan. 2019. Graph attention convolution for point cloud semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10296--10305.
[51]
MengWang, SenWang, Han Yang, Zheng Zhang, Xi Chen, and Guilin Qi. 2021. Is Visual Context Really Helpful for Knowledge Graph? A Representation Learning Perspective. In Proceedings of the ACM International Conference on Multimedia. 2735--2743.
[52]
Mengzhu Wang, Wei Wang, Baopu Li, Xiang Zhang, Long Lan, Huibin Tan, Tianyi Liang, Wei Yu, and Zhigang Luo. 2021. Interbn: Channel fusion for adversarial unsupervised domain adaptation. In Proceedings of the ACM International Conference on Multimedia. 3691--3700.
[53]
Wen Wang, Yang Cao, Jing Zhang, Fengxiang He, Zheng-Jun Zha, Yonggang Wen, and Dacheng Tao. 2021. Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers. In Proceedings of the ACM International Conference on Multimedia. 1730--1738.
[54]
Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, and Bryan Hooi. 2021. Curgraph: Curriculum learning for graph classification. In Proceedings of the Web Conference. 1238--1248.
[55]
Guoqiang Wei, Cuiling Lan, Wenjun Zeng, and Zhibo Chen. 2021. Metaalign: Coordinating domain alignment and classification for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16643--16653.
[56]
Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, and Zhibo Chen. 2021. ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation. In Proceedings of the Conference on Neural Information Processing Systems. 13834--13846.
[57]
Man Wu, Shirui Pan, Chuan Zhou, Xiaojun Chang, and Xingquan Zhu. 2020. Unsupervised domain adaptive graph convolutional networks. In Proceedings of the Web Conference. 1457--1467.
[58]
Haifeng Xia, Taotao Jing, Chen Chen, and Zhengming Ding. 2021. Semisupervised Domain Adaptive Retrieval via Discriminative Hashing Learning. In Proceedings of the ACM International Conference on Multimedia. 3853--3861.
[59]
Ni Xiao and Lei Zhang. 2021. Dynamic weighted learning for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 15242--15251.
[60]
Furong Xu, Meng Wang, Wei Zhang, Yuan Cheng, and Wei Chu. 2021. Discrimination-Aware Mechanism for Fine-grained Representation Learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 813--822.
[61]
Keyulu Xu,Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks?. In Proceedings of the International Conference on Learning Representations.
[62]
Keyulu Xu,Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In Proceedings of the International Conference on Learning Representations.
[63]
Hongliang Yan, Yukang Ding, Peihua Li, Qilong Wang, Yong Xu, and Wangmeng Zuo. 2017. Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2272--2281.
[64]
Longqi Yang, Liangliang Zhang, and Wenjing Yang. 2021. Graph Adversarial Self-Supervised Learning. In Proceedings of the Conference on Neural Information Processing Systems, Vol. 34. 14887--14899.
[65]
Xun Yang, Fuli Feng, Wei Ji, Meng Wang, and Tat-Seng Chua. 2021. Deconfounded video moment retrieval with causal intervention. In Proceedings of the International ACM SIGIR Conference on Research & Development in Information Retrieval. 1--10.
[66]
X Yang, P Zhou, and M Wang. 2019. Person Reidentification via Structural Deep Metric Learning. IEEE Transactions on Neural Networks and Learning Systems 30, 10 (2019), 2987--2998.
[67]
Mucong Ye, Jing Zhang, Jinpeng Ouyang, and Ding Yuan. 2021. Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation. In Proceedings of the ACM International Conference on Multimedia. 2233--2242.
[68]
Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. 2018. Hierarchical graph representation learning with differentiable pooling. In Proceedings of the Conference on Neural Information Processing Systems. 4805--4815.
[69]
Yuning You, Tianlong Chen, Yang Shen, and Zhangyang Wang. 2021. Graph Contrastive Learning Automated. In Proceedings of the International Conference on Machine Learning. 12121--12132.
[70]
Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. Proceedings of the Conference on Neural Information Processing Systems, 5812--5823.
[71]
Werner Zellinger, Thomas Grubinger, Edwin Lughofer, Thomas Natschläger, and Susanne Saminger-Platz. 2017. Central moment discrepancy (cmd) for domain in variant representation learning. In Proceedings of the International Conference on Learning Representations.
[72]
Muhan Zhang, Zhicheng Cui, Marion Neumann, and Yixin Chen. 2018. An end-to-end deep learning architecture for graph classification. In Proceedings of the AAAI Conference on Artificial Intelligence. 4438--4445.
[73]
Shuai Zheng, Zhenfeng Zhu, Xingxing Zhang, Zhizhe Liu, Jian Cheng, and Yao Zhao. 2020. Distribution-induced bidirectional generative adversarial network for graph representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7222--7231.
[74]
Yang Zou, Zhiding Yu, BVK Kumar, and Jinsong Wang. 2018. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European Conference on Computer Vision. 289--305.
[75]
Yang Zou, Zhiding Yu, Xiaofeng Liu, BVK Kumar, and Jinsong Wang. 2019. Confidence regularized self-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5982--5991.

Cited By

View all
  • (2024)S3GCLProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694114(49973-49990)Online publication date: 21-Jul-2024
  • (2024)Pairwise alignment improves graph domain adaptationProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693390(32552-32575)Online publication date: 21-Jul-2024
  • (2024)A survey of data-efficient graph learningProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/896(8104-8113)Online publication date: 3-Aug-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
MM '22: Proceedings of the 30th ACM International Conference on Multimedia
October 2022
7537 pages
ISBN:9781450392037
DOI:10.1145/3503161
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

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 October 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. domain adaption
  2. graph augmentation
  3. graph classification

Qualifiers

  • Research-article

Funding Sources

  • Science and Technology Innovation 2030 ?Brain Science and Brain-like Research Major Project

Conference

MM '22
Sponsor:

Acceptance Rates

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)163
  • Downloads (Last 6 weeks)19
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)S3GCLProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694114(49973-49990)Online publication date: 21-Jul-2024
  • (2024)Pairwise alignment improves graph domain adaptationProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693390(32552-32575)Online publication date: 21-Jul-2024
  • (2024)A survey of data-efficient graph learningProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/896(8104-8113)Online publication date: 3-Aug-2024
  • (2024)Rank and alignProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/520(4706-4714)Online publication date: 3-Aug-2024
  • (2024)GALA: Graph Diffusion-Based Alignment With Jigsaw for Source-Free Domain AdaptationIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2024.341637246:12(9038-9051)Online publication date: Dec-2024
  • (2024)Domain Adaptive Graph ClassificationICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)10.1109/ICASSP48485.2024.10448226(4915-4919)Online publication date: 14-Apr-2024
  • (2024)TO-UGDA: target-oriented unsupervised graph domain adaptationScientific Reports10.1038/s41598-024-59890-y14:1Online publication date: 22-Apr-2024
  • (2023)Topological Structure Learning for Weakly-Supervised Out-of-Distribution DetectionProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612195(4858-4866)Online publication date: 26-Oct-2023
  • (2023)LHAct: Rectifying Extremely Low and High Activations for Out-of-Distribution DetectionProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3611720(8105-8113)Online publication date: 26-Oct-2023
  • (2023)Messages are Never Propagated Alone: Collaborative Hypergraph Neural Network for Time-Series ForecastingIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2023.333138946:4(2333-2347)Online publication date: 9-Nov-2023

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media