Yang, X., Xu, X., Xu, Z., Chu, J., & Hu, J. (2024). DiffGCL: Diffusion model-based Graph Contrastive Learning for Service Recommendation. In R. N. Chang, C. K. Chang, Z. Jiang, J. Yang, Z. Jin, M. Sheng, J. Fan, K. K. Fletcher, Q. He, Q. He, C. Ardagna, J. Yang, J. Yin, Z. Wang, A. Beheshti, S. Russo, N. Atukorala, J. Wu, P. S. Yu, H. Ludwig, S. Reiff-Marganiec, E. Zhang, A. Sailer, N. Bena, K. Li, Y. Watanabe, T. Zhao, S. Wang, Z. Tu, Y. Wang, ... K. Wei (Eds.), Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024 (pp. 310-319). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICWS62655.2024.00053
Yang, Xiuqi ; Xu, Xiaojun ; Xu, Zhuofan et al. / DiffGCL : Diffusion model-based Graph Contrastive Learning for Service Recommendation. Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024. editor / Rong N. Chang ; Carl K. Chang ; Zigui Jiang ; Jingwei Yang ; Zhi Jin ; Michael Sheng ; Jing Fan ; Kenneth K. Fletcher ; Qiang He ; Qiang He ; Claudio Ardagna ; Jian Yang ; Jianwei Yin ; Zhongjie Wang ; Amin Beheshti ; Stefano Russo ; Nimanthi Atukorala ; Jia Wu ; Philip S. Yu ; Heiko Ludwig ; Stephan Reiff-Marganiec ; Emma Zhang ; Anca Sailer ; Nicola Bena ; Kuang Li ; Yuji Watanabe ; Tiancheng Zhao ; Shangguang Wang ; Zhiying Tu ; Yingjie Wang ; Kang Wei. Institute of Electrical and Electronics Engineers Inc., 2024. pp. 310-319
@inproceedings{01648f05bb5e434d84ea8499cd5e0687,
title = "DiffGCL: Diffusion model-based Graph Contrastive Learning for Service Recommendation",
abstract = "Recent years have witnessed the notable resurgence of graph neural networks (GNNs) in service recommender systems. GNN-based service recommender systems heavily rely on the recursive message propagation mechanism between layers. However, they encounter challenges due to data sparsity and susceptibility to noisy interactions, leading to unstable and suboptimal performance. Several studies have attempted to mitigate these issues by integrating GNNs with contrastive learning techniques. Despite their success, most existing approaches utilize either stochastic or heuristic data augmentation methods. We argue that these methods suffer from inherent limitations, including disruption of the original structure of the user-service interaction graph and the need for laborious and iterative experimentation. In this paper, we propose a novel Diffusion model-based Graph Contrastive Learning framework, named DiffGCL, for service recommendation. Specifically, we incorporate Diffusion models into service recommender systems as generators for contrastive learning views. We also introduce a self-adaptive data augmentation strategy that dynamically constructs new dual views each epoch while preserving the intrinsic semantic structure of the generated graph. Extensive experiments conducted on multiple datasets demonstrate the effectiveness of DiffGCL, outperforming various baseline models on service recommendation tasks.",
keywords = "Collaborative Filtering, Contrastive Learning, Diffusion Models, Graph Neural Networks, Service Recommendation",
author = "Xiuqi Yang and Xiaojun Xu and Zhuofan Xu and Jing Chu and Jingjing Hu",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE International Conference on Web Services, ICWS 2024 ; Conference date: 07-07-2024 Through 13-07-2024",
year = "2024",
doi = "10.1109/ICWS62655.2024.00053",
language = "English",
pages = "310--319",
editor = "Chang, {Rong N.} and Chang, {Carl K.} and Zigui Jiang and Jingwei Yang and Zhi Jin and Michael Sheng and Jing Fan and Fletcher, {Kenneth K.} and Qiang He and Qiang He and Claudio Ardagna and Jian Yang and Jianwei Yin and Zhongjie Wang and Amin Beheshti and Stefano Russo and Nimanthi Atukorala and Jia Wu and Yu, {Philip S.} and Heiko Ludwig and Stephan Reiff-Marganiec and Emma Zhang and Anca Sailer and Nicola Bena and Kuang Li and Yuji Watanabe and Tiancheng Zhao and Shangguang Wang and Zhiying Tu and Yingjie Wang and Kang Wei",
booktitle = "Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",
}
Yang, X, Xu, X, Xu, Z, Chu, J & Hu, J 2024, DiffGCL: Diffusion model-based Graph Contrastive Learning for Service Recommendation. in RN Chang, CK Chang, Z Jiang, J Yang, Z Jin, M Sheng, J Fan, KK Fletcher, Q He, Q He, C Ardagna, J Yang, J Yin, Z Wang, A Beheshti, S Russo, N Atukorala, J Wu, PS Yu, H Ludwig, S Reiff-Marganiec, E Zhang, A Sailer, N Bena, K Li, Y Watanabe, T Zhao, S Wang, Z Tu, Y Wang & K Wei (eds), Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024. Institute of Electrical and Electronics Engineers Inc., pp. 310-319, 2024 IEEE International Conference on Web Services, ICWS 2024, Shenzhen, China, 7/07/24. https://doi.org/10.1109/ICWS62655.2024.00053
DiffGCL: Diffusion model-based Graph Contrastive Learning for Service Recommendation. / Yang, Xiuqi; Xu, Xiaojun; Xu, Zhuofan et al.
Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024. ed. / Rong N. Chang; Carl K. Chang; Zigui Jiang; Jingwei Yang; Zhi Jin; Michael Sheng; Jing Fan; Kenneth K. Fletcher; Qiang He; Qiang He; Claudio Ardagna; Jian Yang; Jianwei Yin; Zhongjie Wang; Amin Beheshti; Stefano Russo; Nimanthi Atukorala; Jia Wu; Philip S. Yu; Heiko Ludwig; Stephan Reiff-Marganiec; Emma Zhang; Anca Sailer; Nicola Bena; Kuang Li; Yuji Watanabe; Tiancheng Zhao; Shangguang Wang; Zhiying Tu; Yingjie Wang; Kang Wei. Institute of Electrical and Electronics Engineers Inc., 2024. p. 310-319.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
TY - GEN
T1 - DiffGCL
T2 - 2024 IEEE International Conference on Web Services, ICWS 2024
AU - Yang, Xiuqi
AU - Xu, Xiaojun
AU - Xu, Zhuofan
AU - Chu, Jing
AU - Hu, Jingjing
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Recent years have witnessed the notable resurgence of graph neural networks (GNNs) in service recommender systems. GNN-based service recommender systems heavily rely on the recursive message propagation mechanism between layers. However, they encounter challenges due to data sparsity and susceptibility to noisy interactions, leading to unstable and suboptimal performance. Several studies have attempted to mitigate these issues by integrating GNNs with contrastive learning techniques. Despite their success, most existing approaches utilize either stochastic or heuristic data augmentation methods. We argue that these methods suffer from inherent limitations, including disruption of the original structure of the user-service interaction graph and the need for laborious and iterative experimentation. In this paper, we propose a novel Diffusion model-based Graph Contrastive Learning framework, named DiffGCL, for service recommendation. Specifically, we incorporate Diffusion models into service recommender systems as generators for contrastive learning views. We also introduce a self-adaptive data augmentation strategy that dynamically constructs new dual views each epoch while preserving the intrinsic semantic structure of the generated graph. Extensive experiments conducted on multiple datasets demonstrate the effectiveness of DiffGCL, outperforming various baseline models on service recommendation tasks.
AB - Recent years have witnessed the notable resurgence of graph neural networks (GNNs) in service recommender systems. GNN-based service recommender systems heavily rely on the recursive message propagation mechanism between layers. However, they encounter challenges due to data sparsity and susceptibility to noisy interactions, leading to unstable and suboptimal performance. Several studies have attempted to mitigate these issues by integrating GNNs with contrastive learning techniques. Despite their success, most existing approaches utilize either stochastic or heuristic data augmentation methods. We argue that these methods suffer from inherent limitations, including disruption of the original structure of the user-service interaction graph and the need for laborious and iterative experimentation. In this paper, we propose a novel Diffusion model-based Graph Contrastive Learning framework, named DiffGCL, for service recommendation. Specifically, we incorporate Diffusion models into service recommender systems as generators for contrastive learning views. We also introduce a self-adaptive data augmentation strategy that dynamically constructs new dual views each epoch while preserving the intrinsic semantic structure of the generated graph. Extensive experiments conducted on multiple datasets demonstrate the effectiveness of DiffGCL, outperforming various baseline models on service recommendation tasks.
KW - Collaborative Filtering
KW - Contrastive Learning
KW - Diffusion Models
KW - Graph Neural Networks
KW - Service Recommendation
UR - http://www.scopus.com/inward/record.url?scp=85210254653&partnerID=8YFLogxK
U2 - 10.1109/ICWS62655.2024.00053
DO - 10.1109/ICWS62655.2024.00053
M3 - Conference contribution
AN - SCOPUS:85210254653
SP - 310
EP - 319
BT - Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024
A2 - Chang, Rong N.
A2 - Chang, Carl K.
A2 - Jiang, Zigui
A2 - Yang, Jingwei
A2 - Jin, Zhi
A2 - Sheng, Michael
A2 - Fan, Jing
A2 - Fletcher, Kenneth K.
A2 - He, Qiang
A2 - He, Qiang
A2 - Ardagna, Claudio
A2 - Yang, Jian
A2 - Yin, Jianwei
A2 - Wang, Zhongjie
A2 - Beheshti, Amin
A2 - Russo, Stefano
A2 - Atukorala, Nimanthi
A2 - Wu, Jia
A2 - Yu, Philip S.
A2 - Ludwig, Heiko
A2 - Reiff-Marganiec, Stephan
A2 - Zhang, Emma
A2 - Sailer, Anca
A2 - Bena, Nicola
A2 - Li, Kuang
A2 - Watanabe, Yuji
A2 - Zhao, Tiancheng
A2 - Wang, Shangguang
A2 - Tu, Zhiying
A2 - Wang, Yingjie
A2 - Wei, Kang
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 7 July 2024 through 13 July 2024
ER -
Yang X, Xu X, Xu Z, Chu J, Hu J. DiffGCL: Diffusion model-based Graph Contrastive Learning for Service Recommendation. In Chang RN, Chang CK, Jiang Z, Yang J, Jin Z, Sheng M, Fan J, Fletcher KK, He Q, He Q, Ardagna C, Yang J, Yin J, Wang Z, Beheshti A, Russo S, Atukorala N, Wu J, Yu PS, Ludwig H, Reiff-Marganiec S, Zhang E, Sailer A, Bena N, Li K, Watanabe Y, Zhao T, Wang S, Tu Z, Wang Y, Wei K, editors, Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024. Institute of Electrical and Electronics Engineers Inc. 2024. p. 310-319 doi: 10.1109/ICWS62655.2024.00053