Abstract
Graph neural network-based multitask learning models on multiview graphs have achieved acceptable results in different real-world applications. However, constructing and fine-tuning artificially designed architectures for various multiview graphs are time-consuming and require expert knowledge. To address this challenge, we propose a multitask multiview graph neural architecture search framework called GM2NAS to automatically design multitask multiview model (M2 model) architectures. Specifically, the GM2NAS framework builds M2 model architectures for multiview graph learning and multitask learning. Unlike traditional graph neural architecture search (GNAS) approaches developed for single-task single-view problems, we design a multitask multiview (M2) search space and an unsupervised evaluation strategy to fit GNAS for multitask multiview graph learning. In terms of the search space, we design an effective multitask multiview (M2) search space that precisely allows identifying the optimal operations for multiview graph learning, multiview representation fusion, task-specific attention, and loss weighting to capture informative representation and implicitly transfer and share information among multiple tasks. In terms of the unsupervised evaluation strategy, we introduce an unsupervised evaluation strategy based on unsupervised learning to guide the search algorithm and enable GNAS to deal with multitask multiview graph learning effectively. Then, we explore different search algorithms to identify the optimal combinations of M2 models for multitask multiview graph learning. To validate the effectiveness of GM2NAS, we apply it to node classification and link prediction tasks. Based on the extensive experiments, the results reveal that GM2NAS outperforms the state-of-the-art models on actual multiview graph data.
Similar content being viewed by others
Availability of data and materials
All datasets used in the paper are publicly available.
References
Cai L, Ji S (2020) A multi-scale approach for graph link prediction. In: Proceedings of the conference on artificial intelligence, pp 3308–3315
Wang X, Zhu M, Bo D, Cui P, Shi C, Pei J (2020) AM-GCN: adaptive multi-channel graph convolutional networks. In: Proceedings of the ACM conference on knowledge discovery and data mining, virtual event, pp 1243–1253
Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS (2021) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4–24
Huang H, Song Y, Wu Y, Shi J, Xie X, Jin H (2022) Multitask representation learning with multiview graph convolutional networks. IEEE Trans Neural Netw Learn Syst 33(3):983–995
Hassani K, Ahmadi AHK (2020) Contrastive multi-view representation learning on graphs. In: Proceedings of the international conference on machine learning, pp 4116–4126
Fan S, Wang X, Shi C, Lu E, Lin K, Wang B (2020) One2multi graph autoencoder for multi-view graph clustering. In: Proceedings of the web conference, pp 3070–3076
Chen Z, Zhang X, Cheng X (2022) ASM2TV: an adaptive semi-supervised multi-task multi-view learning framework for human activity recognition. In: Proceedings of the AAAI conference on artificial intelligence, pp 6342–6349
Zhang Z, Wang X, Zhu W (2021) Automated machine learning on graphs: A survey. In: Proceedings of the international joint conference on artificial intelligence, pp 4704–4712
Oloulade BM, Gao J, Chen J, Lyu T, Al-Sabri R (2022) Graph neural architecture search: a survey. Tsinghua Sci Technol 27(4):692–708
Gupta S, Rana S, Saha B, Phung D, Venkatesh S (2016) A new transfer learning framework with application to model-agnostic multi-task learning. Knowl Inf Syst 49(3):933–973
Fifty C, Amid E, Zhao Z, Yu T, Anil R, Finn C (2021) Efficiently identifying task groupings for multi-task learning. Adv Neural Inf Process Syst 34(8):27503–27516
Hong C, Yu J, Zhang J, Jin X, Lee K-H (2018) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Ind Inf 15(7):3952–3961
Zhang J, Su Q, Tang B, Wang C, Li Y (2021) Dpsnet: multitask learning using geometry reasoning for scene depth and semantics. IEEE Trans Neural Netw Learn Syst 1(1):1–12
Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670
Hong C, Yu J, Tao D, Wang M (2014) Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval. IEEE Trans Ind Electronics 62(6):3742–3751
Lu X, Zhu L, Li J, Zhang H, Shen HT (2019) Efficient supervised discrete multi-view hashing for large-scale multimedia search. IEEE Trans Multimedia 22(8):2048–2060
Lu X, Zhu L, Cheng Z, Nie L, Zhang H (2019) Online multi-modal hashing with dynamic query-adaption. In: Proceedings of the international ACM SIGIR conference on research and development in information retrieval, pp 715–724
Lu X, Zhu L, Cheng Z, Li J, Nie X, Zhang H (2019) Flexible online multi-modal hashing for large-scale multimedia retrieval. In: Proceedings of the ACM international conference on multimedia, pp 1129–1137
Zhang J, Su Q, Wang C, Gu H (2020) Monocular 3d vehicle detection with multi-instance depth and geometry reasoning for autonomous driving. Neurocomputing 403(1):182–192
Vandenhende S, Georgoulis S, Gool LV (2020) Mti-net: Multi-scale task interaction networks for multi-task learning. In: European conference on computer vision, pp 527–543
Xiao S, Wang S, Dai Y, Guo W (2022) Graph neural networks in node classification: survey and evaluation. Machine Vis Appl 33(1):1–19
Tran PV (2018) Multi-task graph autoencoders. In Proceedings of the NIPS workshop on relational representation learning, pp 1–9
Ma Y, Ren Z, Jiang Z, Tang J, Yin D (2018) Multi-dimensional network embedding with hierarchical structure. In: Proceedings of the ACM international conference on web search and data mining, pp 387–395
Qu M, Tang J, Shang J, Ren X, Zhang M, Han J (2017) An attention-based collaboration framework for multi-view network representation learning. In: Proceedings of the ACM on conference on information and knowledge management, pp 1767–1776
Wu J, Hong Z, Pan S, Zhu X, Cai Z, Zhang C (2016) Multi-graph-view subgraph mining for graph classification. Knowl Inf Syst 48(1):29–54
Lu C, He L, Shao W, Cao B, Yu PS (2017) Multilinear factorization machines for multi-task multi-view learning. In: Proceedings of the ACM international conference on web search and data mining, pp 701–709
Wang M, Lin Y, Lin G, Yang K, Wu X-m (2020) M2grl: A multi-task multi-view graph representation learning framework for web-scale recommender systems. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining, pp 2349–2358
Li Y, King I (2020) Autograph: Automated graph neural network. In: Proceedings of the international conference on neural information processing, pp 189–201
Zhao H, Wei L, Yao Q (2020) Simplifying architecture search for graph neural network. In: Proceedings of the ACM international conference on information and knowledge management, pp 1–12
Chen J, Gao J, Chen Y, Oloulade MB, Lyu T, Li Z (2021) Graphpas: Parallel architecture search for graph neural networks. In: Proceedings of the international ACM conference on research and development in information retrieval, pp 2182–2186
Yoon M, Gervet T, Hooi B, Faloutsos C (2020) Autonomous graph mining algorithm search with best speed/accuracy trade-off. In: Proceedings of the IEEE international conference on data mining, pp 751–760
Chaudhari S, Mithal V, Polatkan G, Ramanath R (2021) An attentive survey of attention models. ACM Trans Intell Syst Technol 12(5):1–32
Yan X, Hu S, Mao Y, Ye Y, Yu H (2021) Deep multi-view learning methods: a review. Neurocomputing 448(1):106–129
Li Y, Yang M, Zhang Z (2019) A survey of multi-view representation learning. IEEE Trans Knowl Data Eng 31(10):1863–1883
Lin B, Ye F, Zhang Y (2021) A closer look at loss weighting in multi-task learning. arXiv preprint arXiv:2111.10603
Shi M, Tang Y, Zhu X, Huang Y, Wilson DA, Zhuang Y, Liu J (2022) Genetic-gnn: Evolutionary architecture search for graph neural networks. Knowl Based Syst 247(1):108–128
You J, Ying Z, Leskovec J (2020) Design space for graph neural networks 10(1):1–12
Li Q, Han Z, Wu X (2018) Deeper insights into graph convolutional networks for semi-supervised learning. In: Proceedings of the AAAI conference on artificial intelligence, pp 3538–3545
Tang L, Liu H (2009) Relational learning via latent social dimensions. In: Proceedings of the ACM international conference on knowledge discovery and data mining, pp 817–826
Ramos J (2003) Using tf-idf to determine word relevance in document queries. In: Proceedings of the instructional conference on machine learning, pp 29–48
Dong Y, Chawla NV, Swami A (2017) metapath2vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the ACM international conference on knowledge discovery and data mining, pp 135–144
De Domenico M, Lima A, Mougel P, Musolesi M (2013) The anatomy of a scientific rumor. Sci Rep 3(1):1–9
Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) LINE: large-scale information network embedding. In: Proceedings of the international conference on world wide web, pp 1067–1077
Zafarani R, Liu H (2009) Social computing data repository at asu \url{http://socialcomputing.asu.edu}. Arizona State University, School of Computing, Informatics and Decision Systems Engineering
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the ACM international conference on knowledge discovery and data mining, pp 701–710
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceddings of the international conference on learning representations, pp 1–12
Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2015) Graph attention networks. In: Proceedings of the international conference on learning representations, pp 1–20
Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Adv Neural Inf Process Syst 30(1):1024–1034
Schlichtkrull MS, Kipf TN, Bloem P, van den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: Proceedings of the semantic web international conference, pp 593–607
Fu T, Lee W, Lei Z (2017) Hin2vec: Explore meta-paths in heterogeneous information networks for representation learning. In: Proceedings of the ACM conference on information and knowledge management, pp 1797–1806
Xie Y, Zhang Y, Gong M, Tang Z, Han C (2020) Mgat: Multi-view graph attention networks. Neural Netw 132(1):180–189
Sun X, Panda R, Feris R, Saenko K (2020) Adashare: learning what to share for efficient deep multi-task learning. Adv Neural Inf Process Syst 33(1):8728–8740
Li Z, Liu F, Yang W, Peng S, Zhou J (2021) A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst
Acknowledgements
The work is supported by the National Natural Science Foundation of China (No. 62272487), Hunan Provincial Science and Technology Program (No. 2021JJ30055).
Funding
The work is supported by the National Natural Science Foundation of China (No. 62272487), Hunan Provincial Science and Technology Program (No. 2021JJ30055).
Author information
Authors and Affiliations
Contributions
JG contributed to investigation, project administration, supervision, validation, and review. RA was involved in conceptualization, data curation, formal analysis, investigation, methodology, resources, validation, visualization, writing, and review and provided software. BMO contributed to investigation, resources, editing, and review. JC was involved in data curation, editing, investigation, resources, validation, and review. TL contributed to investigation, validation, and review. ZW was involved in investigation, validation, and review.
Corresponding author
Ethics declarations
Conflict of interest
No conflicts of interest or competing interests
Ethics approval
Not applicable
Consent to participate
The manuscript is approved by all authors for publication.
Consent for publication
All authors who participated in this study give the publisher permission to publish this work.
Code availability
Please email alsabriraeed@csu.edu.cn to request code for the proposed method.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gao, J., Al-Sabri, R., Oloulade, B.M. et al. GM2NAS: multitask multiview graph neural architecture search. Knowl Inf Syst 65, 4021–4054 (2023). https://doi.org/10.1007/s10115-023-01886-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-023-01886-7