Towards Lightweight Cross-Domain Sequential Recommendation via Tri-Branches Graph External Attention Network

Zhang Jinyu; Ma Chenxi; Li Chao; Zhao Zhongying

doi:10.7544/issn1000-1239.202440197

Journal of Computer Research and Development > 2024 > 61(8): 1930-1944. > DOI: 10.7544/issn1000-1239.202440197

Zhang Jinyu, Ma Chenxi, Li Chao, Zhao Zhongying. Towards Lightweight Cross-Domain Sequential Recommendation via Tri-Branches Graph External Attention Network[J]. Journal of Computer Research and Development, 2024, 61(8): 1930-1944. DOI: 10.7544/issn1000-1239.202440197

Citation:

PDF (1867 KB)

Towards Lightweight Cross-Domain Sequential Recommendation via Tri-Branches Graph External Attention Network

College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266590

Funds: This work was supported by the National Natural Science Foundation of China (62072288), the Taishan Scholar Program of Shandong Province (tsqn202211154), and the Natural Science Foundation of Shandong Province (ZR2022MF268).

More Information

Author Bio:
Zhang Jinyu: born in 1996. PhD candidate. Student member of CCF. His main research interests include sequential recommendation and lightweight recommendation

Ma Chenxi: born in 1998. Master candidate. Her main research interest includes cross-domain sequential recommendation

Li Chao: born in 1984. PhD, associate professor. Senior member of CCF. His main research interests include graph data mining and recommendation algorithm

Zhao Zhongying: born in 1983. PhD, professor. Distinguished member of CCF. Her main research interests include graph data mining and recommendation system
Received Date: March 15, 2024
Revised Date: April 28, 2024
Available Online: May 16, 2024

Graphical Abstract

Abstract

Abstract

Cross-domain sequential recommendation (CSR) aims to capture the behavioral preferences of users by modeling their historical interaction sequences in multiple domains, thus providing personalized cross-domain recommendations. Recently, researchers have started integrating graph convolution networks (GCNs) into CSR to model complicated associations among users and items. However, due to their complicated structure, most graph-based CSR methods are usually accompanied by high computational complexity or memory overhead, making them difficult to deploy on resource-constrained edge devices. Besides, existing lightweight graph-based CSR methods tend to employ single layer aggregating protocol (SLAP) to propagate embeddings on cross-domain sequential graphs (CSG). Such a strategy indeed aids the GCNs in circumventing cross-domain noise interference caused by high-order neighborhood aggregation strategies. However, it also shields GCN from mining high-order sequential relationships within individual domains. To this end, we introduce a lightweight tri-branches graph external attention network (TEA-Net). Specifically, we separate the original CSG into three parts including two inner-domain sequential graphs and an inter-domain sequential graph and devise a parallel tri-branches graph convolution network to learn the node representations. This structure can simultaneously consider the first-order inter-domain correlations and the high-order inner-domain connectivity without introducing additional cross-domain noises. Besides, we propose an improved external attention (EA) component without the nonlinear channel, which captures the sequential dependency among items at a lower cost and shares attention weights across multiple branches. We conduct extensive experiments on two large-scale real-world datasets to verify the performance of TEA-Net. The experimental results demonstrate the superiority of TEA-Net in both the lightweight performance and the prediction accuracy compared with several state-of-the-art methods.

FullText(HTML)

References (43)

References

[1]	He Xiangnan, Liao Lizi, Zhang Hanwang, et al. Neural collaborative filtering[C]//Proc of the 26th Int Conf on World Wide Web. New York: ACM, 2017: 173−182
[2]	Hidasi B, Karatzoglou A, Baltrunas L, et al. Session-based recommendations with recurrent neural networks[C]//Proc of the 4th Int Conf on Learning Representations, New York: penReview. net, 2016: 1−10
[3]	Li Yang, Chen Tong, Zhang Pengfei, et al. Lightweight self-attentive sequential recommendation[C]//Proc of the 30th ACM Int Conf on Information and Knowledge Management. New York: ACM, 2021: 967−977
[4]	Zheng Xiaolin, Su Jiajie, Liu Weiming, et al. DDGHM: Dual dynamic graph with hybrid metric training for cross-domain sequential recommendation[C]//Proc of the 30th ACM Int Conf on Multimedia. New York: ACM, 2022: 471−481
[5]	Ma Muyang, Ren Pengjie, Lin Yujie, et al. π-Net: A parallel information-sharing network for shared-account cross-domain sequential recommendations[C]//Proc of the 42nd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2019: 685−694
[6]	Sun Wenchao, Ma Muyang, Ren Pengjie, et al. Parallel split-join networks for shared account cross-domain sequential recommendations[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(4): 4106−4123 doi: 10.1109/TKDE.2021.3130927
[7]	Chen Chen, Guo Jie, Song Bin. Dual attention transfer in session-based recommendation with multi-dimensional integration[C]//Proc of the 44th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2021: 869−878
[8]	Li Pan, Jiang Zhichao, Que Maofei, et al. Dual attentive sequential learning for cross-domain click-through rate prediction[C]//Proc of the 27th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2021: 3172−3180
[9]	Guo Lei, Tang Li, Chen Tong, et al. DA-GCN: A domain-aware attentive graph convolution network for shared-account cross-domain sequential recommendation[C]//Proc of the 30th Int Joint Conf on Artificial Intelligence. Amsterdam: Elsevier, 2021: 2483−2489
[10]	Guo Lei, Zhang Jinyu, Tang Li, et al. Time interval-enhanced graph neural network for shared-account cross-domain sequential recommendation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(3): 4002−4016 doi: 10.1109/TNNLS.2022.3201533
[11]	Chen Tong, Yin Hongzhi, Zheng Yujia, et al. Learning elastic embeddings for customizing on-device recommenders[C]//Proc of the 27th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2021: 138−147
[12]	Miao Hang, Li Anchen, Yang Bo. Meta-path enhanced lightweight graph neural network for social recommendation[C]//Proc of the 27th Int Conf on Database Systems for Advanced Applications. Berlin: Springer, 2022: 134−149
[13]	Wang Ruiqin, Lou Jungang, Jiang Yunliang. LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation[J]. Expert Systems with Applications, 2023, 232: 120741 doi: 10.1016/j.eswa.2023.120741
[14]	Zhang Jinyu, Duan Huichuan, Guo Lei, et al. Towards lightweight cross-domain sequential recommendation via external attention-enhanced graph convolution network[C]//Proc of the 28th Int Conf on Database Systems for Advanced Applications. Berlin: Springer, 2023: 205−220
[15]	Cheng Chen, Yang Haiqin, Michael R T L, et al. Where you like to go next: Successive point-of-interest recommendation[C]//Proc of the 23rd Int Joint Conf on Artificial Intelligence. Amsterdam: Elsevier, 2013: 2605–2611
[16]	He Ruining, Kang Wangcheng, McAuley J. Translation-based recommendation[C]//Proc of the 11th ACM Conf on Recommender Systems. New York: ACM, 2017: 161−169
[17]	宋威,乔阳阳. 基于加权序列模式的推荐算法研究[J]. 计算机工程与科学,2015,37(7):1399−1404 doi: 10.3969/j.issn.1007-130X.2015.07.028 Song Wei, Qiao Yangyang. Research on the recommender algorithm based on weighted sequential patterns[J]. Journal of Computer Engineering and Science, 2015, 37(7): 1399−1404 (in Chinese) doi: 10.3969/j.issn.1007-130X.2015.07.028
[18]	邢春晓,高凤荣,战思南,等. 适应用户兴趣变化的协同过滤推荐算法[J]. 计算机研究与发展,2007,44(2):296−301 Xing Chunxiao, Gao Fengrong, Zhan Sinan, et al. A collaborative filtering recommendation algorithm incorporated with user interest change[J]. Journal of Computer Research and Development, 2007, 44(2): 296−301 (in Chinese)
[19]	Zheng Yujia, Liu Siyi, Li Zekun, et al. DGTN: dual-channel graph transition network for session-based recommendation[C]//Proc of the 2020 Int Conf on Data Mining Workshops. Piscataway, NJ: IEEE, 2020: 236−242
[20]	Qiu Ruihong, Huang Zi, Yin Hongzhi, et al. Contrastive learning for representation degeneration problem in sequential recommendation[C]//Proc of the 15th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2022: 813−823
[21]	赵容梅,孙思雨,鄢凡力,等. 基于对比学习的多兴趣感知序列推荐系统[J/OL]. 计算机研究与发展,[2024−03−12]. http://kns.cnki.net/kcms/ detail/11.1777.TP.20240105.1351.010.html Zhao Rongmei, Sun Siyu, Yan Fanli, et al. Multi-interest aware sequential recommender system based on contrastive learning[J]. Journal of Computer Research and Development, [2024−03−12]. http://kns.cnki.net/kcms/ detail/11.1777.TP.20240105.1351.010.html (in Chinese)
[22]	Quadrana M, Karatzoglou A, Hidasi B, et al. Personalizing session-based recommendations with hierarchical recurrent neural networks[C]//Proc of the 11th ACM Conf on Recommender Systems. New York: ACM, 2017: 130−137
[23]	Wu Chaoyuan, Ahmed A, Beutel A, et al. Recurrent recommender networks[C]//Proc of the 10th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2017: 495−503
[24]	Zhang Mengqi, Wu Shu, Yu Xueli, et al. Dynamic graph neural networks for sequential recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(5): 4741−4753
[25]	Zhu Tianyu, Sun Leilei, Chen Guoqing. Graph-based embedding smoothing for sequential recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 35(1): 496−508
[26]	Chen Huiyuan, Lin Yusan, Pan Menghai, et al. Denoising self-attentive sequential recommendation[C]//Proc of the 16th ACM Conf on Recommender Systems. New York: ACM, 2022: 92−101
[27]	Xie Jiayi, Chen Zhenzhong. Hierarchical transformer with spatio-temporal context aggregation for next point-of-interest recommendation[J]. ACM Transactions on Information Systems, 2023, 42(2): 1−30
[28]	Lin Zhuoyi, Zang Sheng, Wang Rundong, et al. Attention over self-attention: Intention-aware re-ranking with dynamic transformer encoders for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(8): 7782−7795
[29]	Xie Xu, Sun Fei, Liu Zhaoyang, et al. Contrastive learning for sequential recommendation[C]//Proc of the 38th Int Conf on Data Engineering. Piscataway, NJ: IEEE, 2022: 1259−1273
[30]	Ma Muyang, Ren Pengjie, Chen Zhumin, et al. Mixed information flow for cross-domain sequential recommendations[J]. ACM Transactions on Knowledge Discovery from Data, 2022, 16(4): 1−32
[31]	郭磊,李秋菊,刘方爱,等. 基于自注意力网络的共享账户跨域序列推荐[J]. 计算机研究与发展,2021,58(11):2524−2537 doi: 10.7544/issn1000-1239.2021.20200564 Guo Lei, Li Qiuju, Liu Fang’ai, et al. Shared-account cross-domain sequential recommendation with self-attention network[J]. Journal of Computer Research and Development, 2021, 58((11): ): 2524−2537 (in Chinese) doi: 10.7544/issn1000-1239.2021.20200564
[32]	任豪,刘柏嵩,孙金杨,等. 基于时间和关系感知的图协同过滤跨域序列推荐[J]. 计算机研究与发展,2023,60(1):112−124 doi: 10.7544/issn1000-1239.202110545 Ren Hao, Liu Baisong, Sun Jinyang, et al. A time and relation-aware graph collaborative filtering for cross-domain sequential recommendation[J]. Journal of Computer Research and Development, 2023, 60(1): 112−124 (in Chinese) doi: 10.7544/issn1000-1239.202110545
[33]	Liu Siyi, Gao Chen, Chen Yihong, et al. Learnable embedding sizes for recommender systems[C]//Proc of the 9th Int Conf on Learning Representations, Virtual: OpenReview. net, 2021: 1−17
[34]	He Xiangnan, Deng Kuan, Wang Xiang, et al. LightGCN: Simplifying and powering graph convolution network for recommendation[C]//Proc of the 43rd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2020: 639−648
[35]	Guo Menghao, Liu Zhengning, Mu Taijiang, et al. Beyond self-attention: external attention using two linear layers for visual tasks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(5): 5436−5447
[36]	Mei M J, Zuber C, Khazaeni Y. A lightweight transformer for next-item product recommendation[C]//Proc of the 16th ACM Conf on Recommender Systems. New York: ACM, 2022: 546−549
[37]	Zhuang Fuzhen, Zhou Yingmin, Ying Haochao, et al. Sequential recommendation via cross-domain novelty seeking trait mining[J]. Journal of Computer Science and Technology, 2020, 35: 305−319 doi: 10.1007/s11390-020-9945-z
[38]	Fu Wenjing, Peng Zhaohui, Wang Senzhang, et al. Deeply fusing reviews and contents for cold start users in cross-domain recommendation systems[C]//Proc of the AAAI Conf on Artificial Intelligence. Menlo Park, CA: AAAI, 2019: 94−101
[39]	Guo Lei, Zhang Jinyu, Chen Tong, et al. Reinforcement learning-enhanced shared-account cross-domain sequential recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(7): 7397−7411
[40]	Li Xunkai, Guo Ronghui, Chen Jianwen, et al. Neural graph collaborative filtering[C]//Proc of the 42nd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2019: 165−174
[41]	Kang Wangcheng, McAuley J. Self-attentive sequential recommendation[C]//Proc of the Int Conf on Data Mining. Piscataway, NJ: IEEE, 2018: 197−206
[42]	Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[C]//Proc of the 30th Int Conf on Artificial Intelligence and Statistics. Palermo, Sicily, Italy: JMLR, 2010: 249−256
[43]	Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint, arXiv: 1412.6980, 2014

[1]	Jiang Xuyan, Quan Wei, Fu Wenwen, Zhang Xiaoliang, Sun Zhigang. OpenPlanner: An Open-Source Traffic Planning Software for Time-Sensitive Networking[J]. Journal of Computer Research and Development. DOI: 10.7544/issn1000-1239.202330776
[2]	Zhang Junna, Bao Xiang, Chen Jiawei, Zhao Xiaoyan, Yuan Peiyan, Wang Shangguang. A Dependent Task Offloading Method for Joint Time Delay and Energy Consumption[J]. Journal of Computer Research and Development, 2023, 60(12): 2770-2782. DOI: 10.7544/issn1000-1239.202220779
[3]	Zheng Yingying, Zhou Junlong, Shen Yufan, Cong Peijin, Wu Zebin. Time and Energy-Sensitive End-Edge-Cloud Resource Provisioning Optimization Method for Collaborative Vehicle-Road Systems[J]. Journal of Computer Research and Development, 2023, 60(5): 1037-1052. DOI: 10.7544/issn1000-1239.202220734
[4]	Gong Xiaohang, Jiang Binze, Chen Xianglan, Gao Yinkang, Li Xi. Survey of Real-Time Computer System Architecture[J]. Journal of Computer Research and Development, 2023, 60(5): 1021-1036. DOI: 10.7544/issn1000-1239.202220731
[5]	Zhang Tong, Feng Jiaqi, Ma Yanying, Qu Siyuan, Ren Fengyuan. Survey on Traffic Scheduling in Time-Sensitive Networking[J]. Journal of Computer Research and Development, 2022, 59(4): 747-764. DOI: 10.7544/issn1000-1239.20210203
[6]	Quan Wei, Fu Wenwen, Sun Zhigang, Li Tao. HX-DS09: A Customized Low Power Time Sensitive Networking Chip for High-End Equipment[J]. Journal of Computer Research and Development, 2021, 58(6): 1242-1245. DOI: 10.7544/issn1000-1239.2021.20210164
[7]	Sha Letian, Fu Jianming, Chen Jing, and Huang Shiyong. A Sensitivity Measurement for Sensitive Information Processing[J]. Journal of Computer Research and Development, 2014, 51(5): 1050-1060.
[8]	Hou Yongshuai, Zhang Yaoyun, Wang Xiaolong, Chen Qingcai, Wang Yuliang, and Hu Baotian. Recognition and Retrieval of Time-sensitive Question in Chinese QA System[J]. Journal of Computer Research and Development, 2013, 50(12): 2612-2620.
[9]	Zhou Hang, Huang Zhiqiu, Zhu Yi, Xia Liang, Liu Linyuan. Real-Time Systems Contact Checking and Resolution Based on Time Petri Net[J]. Journal of Computer Research and Development, 2012, 49(2): 413-420.
[10]	Zhou Hang, Huang Zhiqiu, Hu Jun, Zhu Yi. Real-Time System Resource Conflict Checking Based on Time Petri Nets[J]. Journal of Computer Research and Development, 2009, 46(9): 1578-1585.

Cited By

Cited by

Periodical cited type(7)

1.	马辉，王瑞琴，杨帅. 一种渐进式增长条件生成对抗网络模型. 电信科学. 2023(06): 105-113 .
2.	杨华芬. 云存储环境下大数据实时动态迁移算法研究. 机械设计与制造工程. 2021(02): 117-122 .
3.	何少芳，沈陆明，谢红霞. 生成式对抗网络的土壤有机质高光谱估测模型. 光谱学与光谱分析. 2021(06): 1905-1911 .
4.	卢锦玲，张梦雪，郭鲁豫. 基于GAN的不平衡负荷数据类型辨识方法. 电力科学与工程. 2021(06): 26-34 .
5.	刘言林. 基于条件生成对抗网络的小样本机器学习数据处理算法研究. 宁夏师范学院学报. 2021(10): 66-73 .
6.	杨彦荣，宋荣杰，周兆永. 基于GAN-PSO-ELM的网络入侵检测方法. 计算机工程与应用. 2020(12): 66-72 .
7.	金秋，林馥. 定向网络中隐藏可逆数据的分层追踪算法. 计算机仿真. 2020(10): 226-229+277 .