research-article

Decentralized Collaborative Learning Framework for Next POI Recommendation

Authors:
Jing Long

The University of Queensland, Brisbane, QLD, Australia

The University of Queensland, Brisbane, QLD, Australia

0000-0003-0848-2158
View Profile

,
Tong Chen

The University of Queensland, Brisbane, QLD, Australia

The University of Queensland, Brisbane, QLD, Australia

0000-0001-7269-146X
View Profile

,
Quoc Viet Hung Nguyen

Griffith University, Brisbane, QLD, Australia

Griffith University, Brisbane, QLD, Australia

0000-0002-9687-1315
View Profile

,
Hongzhi Yin

The University of Queensland, Brisbane, QLD, Australia

The University of Queensland, Brisbane, QLD, Australia

0000-0003-1395-261X
View Profile

Authors Info & Claims

ACM Transactions on Information Systems Volume 41 Issue 3Article No.: 66pp 1–25https://doi.org/10.1145/3555374

Published:07 February 2023Publication History

ACM Transactions on Information Systems

Abstract

Next Point-of-Interest (POI) recommendation has become an indispensable functionality in Location-based Social Networks (LBSNs) due to its effectiveness in helping people decide the next POI to visit. However, accurate recommendation requires a vast amount of historical check-in data, thus threatening user privacy as the location-sensitive data needs to be handled by cloud servers. Although there have been several on-device frameworks for privacy-preserving POI recommendations, they are still resource intensive when it comes to storage and computation, and show limited robustness to the high sparsity of user-POI interactions. On this basis, we propose a novel decentralized collaborative learning framework for POI recommendation (DCLR), which allows users to train their personalized models locally in a collaborative manner. DCLR significantly reduces the local models’ dependence on the cloud for training, and can be used to expand arbitrary centralized recommendation models. To counteract the sparsity of on-device user data when learning each local model, we design two self-supervision signals to pretrain the POI representations on the server with geographical and categorical correlations of POIs. To facilitate collaborative learning, we innovatively propose to incorporate knowledge from either geographically or semantically similar users into each local model with attentive aggregation and mutual information maximization. The collaborative learning process makes use of communications between devices while requiring only minor engagement from the central server for identifying user groups, and is compatible with common privacy preservation mechanisms like differential privacy. We evaluate DCLR with two real-world datasets, where the results show that DCLR outperforms state-of-the-art on-device frameworks and yields competitive results compared with centralized counterparts.

REFERENCES

[1] Botev Zdravko I., Grotowski Joseph F., and Kroese Dirk P.. 2010. Kernel density estimation via diffusion. Annals of Statistics 38, 5 (2010), 2916–2957.Google ScholarCross Ref
[2] Chang Buru, Park Yonggyu, Park Donghyeon, Kim Seongsoon, and Kang Jaewoo. 2018. Content-aware hierarchical point-of-interest embedding model for successive POI recommendation. In International Joint Conferences on Artificial Intelligence (IJCAI’22). 3301–3307.Google ScholarCross Ref
[3] Chen Chaochao, Liu Ziqi, Zhao Peilin, Zhou Jun, and Li Xiaolong. 2018. Privacy preserving point-of-interest recommendation using decentralized matrix factorization. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32. No. 1.Google ScholarCross Ref
[4] Chen Hongxu, Yin Hongzhi, Sun Xiangguo, Chen Tong, Gabrys Bogdan, and Musial Katarzyna. 2020. Multi-level graph convolutional networks for cross-platform anchor link prediction. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1503–1511.Google ScholarDigital Library
[5] Cheng Chen, Yang Haiqin, Lyu Michael R., and King Irwin. 2013. Where you like to go next: Successive point-of-interest recommendation. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI’13). AAAI Press, 2605–2611.Google Scholar
[6] Davies Jack N., Hobson Graeme E., and McGlasson W. B.. 1981. The constituents of tomato fruit—the influence of environment, nutrition, and genotype. Critical Reviews in Food Science & Nutrition 15, 3 (1981), 205–280.Google ScholarCross Ref
[7] Duriakova Erika, Tragos Elias Z., Smyth Barry, Hurley Neil, Peña Francisco J., Symeonidis Panagiotis, Geraci James, and Lawlor Aonghus. 2019. PDMFRec: A decentralised matrix factorisation with tunable user-centric privacy. In Proceedings of the 13th ACM Conference on Recommender Systems. 457–461.Google ScholarDigital Library
[8] Dwork Cynthia, Roth Aaron, et al. 2014. The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science 9, 3–4 (2014), 211–407.Google ScholarDigital Library
[9] Fan Mingming and Khademi Maryam. 2014. Predicting a business star in Yelp from its reviews text alone. CoRR abs/1401.0864 (2014). arXiv:1401.0864 http://arxiv.org/abs/1401.0864.Google Scholar
[10] Feng Jie, Li Yong, Zhang Chao, Sun Funing, Meng Fanchao, Guo Ang, and Jin Depeng. 2018. DeepMove: Predicting human mobility with attentional recurrent networks. In Proceedings of the 2018 World Wide Web Conference (WWW’18). 1459–1468.Google ScholarDigital Library
[11] Giantomassi Andrea, Ferracuti Francesco, Iarlori Sabrina, Ippoliti Gianluca, and Longhi Sauro. 2015. Electric motor fault detection and diagnosis by kernel density estimation and Kullback-Leibler divergence based on stator current measurements. IEEE Transactions on Industrial Electronics 62 (2015), 1770–1780.Google ScholarCross Ref
[12] Guo Qing, Sun Zhu, Zhang Jie, and Theng Yin-Leng. 2020. An attentional recurrent neural network for personalized next location recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 83–90.Google ScholarCross Ref
[13] Guo Yeting, Liu Fang, Cai Zhiping, Zeng Hui, Chen Li, Zhou Tongqing, and Xiao Nong. 2021. PREFER: Point-of-interest REcommendation with efficiency and privacy-preservation via federated edge learning. Proceedings of ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, 1 (2021), 1–25.Google ScholarDigital Library
[14] Han Peng, Li Zhongxiao, Liu Yong, Zhao Peilin, Li Jing, Wang Hao, and Shang Shuo. 2020. Contextualized point-of-interest recommendation. In International Joint Conferences on Artificial Intelligence, Article 344. 2484–2490.Google Scholar
[15] Hochreiter Sepp and Schmidhuber Jürgen. 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780.Google ScholarDigital Library
[16] Hull Gordon, Lipford Heather Richter, and Latulipe Celine. 2010. Contextual gaps: Privacy issues on facebook. Ethics and Information Technology 13, 4 (2010), 289–302.Google ScholarDigital Library
[17] Kalathil Dileep, Nayyar Naumaan, and Jain Rahul. 2014. Decentralized learning for multiplayer multiarmed bandits. IEEE Transactions on Information Theory 60, 4 (2014), 2331–2345.Google ScholarDigital Library
[18] Kang Wang-Cheng and McAuley Julian. 2018. Self-attentive sequential recommendation. In 2018 IEEE International Conference on Data Mining (ICDM’18). IEEE, 197–206.Google ScholarCross Ref
[19] Kong Lingpeng, d’Autume Cyprien de Masson, Ling Wang, Yu Lei, Dai Zihang, and Yogatama Dani. 2019. A mutual information maximization perspective of language representation learning. arXiv preprint arXiv:1910.08350 (2019).Google Scholar
[20] Krichene Walid and Rendle Steffen. 2020. On sampled metrics for item recommendation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1748–1757.Google ScholarDigital Library
[21] Leng Cong, Wu Jiaxiang, Cheng Jian, Zhang Xi, and Lu Hanqing. 2015. Hashing for distributed data. In International Conference on Machine Learning. PMLR, 1642–1650.Google Scholar
[22] Li Ranzhen, Shen Yanyan, and Zhu Yanmin. 2018. Next point-of-interest recommendation with temporal and multi-level context attention. In 2018 IEEE International Conference on Data Mining (ICDM’18). 1110–1115.Google ScholarCross Ref
[23] Li Yang, Chen Tong, Yin Hongzhi, and Huang Zi. 2021. Discovering collaborative signals for next POI recommendation with iterative seq2graph augmentation. arXiv: arXiv preprint arXiv:2106.15814.Google Scholar
[24] Lian Defu, Wu Yongji, Ge Yong, Xie Xing, and Chen Enhong. 2020. Geography-Aware Sequential Location Recommendation. Association for Computing Machinery, New York, NY, 2009–2019. Google ScholarDigital Library
[25] Lian Defu, Zhao Cong, Xie Xing, Sun Guangzhong, Chen Enhong, and Rui Yong. 2014. GeoMF: Joint geographical modeling and matrix factorization for point-of-interest recommendation. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’14). Association for Computing Machinery, New York, NY, 831–840. Google ScholarDigital Library
[26] Liao Yongjun, Geurts Pierre, and Leduc Guy. 2010. Network distance prediction based on decentralized matrix factorization. In International Conference on Research in Networking. Springer, 15–26.Google ScholarDigital Library
[27] Liu Qiang, Wu Shu, Wang Liang, and Tan Tieniu. 2016. Predicting the next location: A recurrent model with spatial and temporal contexts. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI’16). AAAI Press, 194–200.Google ScholarCross Ref
[28] Liu Xin, Liu Yong, Aberer Karl, and Miao Chunyan. 2013. Personalized point-of-interest recommendation by mining users’ preference transition. In Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. 733–738.Google ScholarDigital Library
[29] Liu Yong, Wei Wei, Sun Aixin, and Miao Chunyan. 2014. Exploiting geographical neighborhood characteristics for location recommendation. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. 739–748.Google ScholarDigital Library
[30] Long Yan, Zhao Pengpeng, Sheng Victor S., Liu Guanfeng, Xu Jiajie, Wu Jian, and Cui Zhiming. 2017. Social personalized ranking embedding for Next POI recommendation. In Web Information Systems Engineering (WISE’17). Lecture Notes in Computer Science, Vol. 10569. Springer International Publishing, Cham, 91–105.Google Scholar
[31] Luo Yingtao, Liu Qiang, and Liu Zhaocheng. 2021. STAN: Spatio-temporal attention network for next location recommendation. In Proceedings of the 2021 World Wide Web Conference (WWW’21). 2177–2185.Google ScholarDigital Library
[32] MacQueen James et al. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1. Oakland, CA, 281–297.Google Scholar
[33] Narayanan A. and Shmatikov V.. 2008. Robust de-anonymization of large sparse datasets. In 2008 IEEE Symposium on Security and Privacy (SP’08). IEEE, 111–125.Google Scholar
[34] Nguyen Quoc Viet Hung, Duong Chi Thang, Nguyen Thanh Tam, Weidlich Matthias, Aberer Karl, Yin Hongzhi, and Zhou Xiaofang. 2017. Argument discovery via crowdsourcing. VLDB Journal 26, 4 (2017), 511–535.Google ScholarCross Ref
[35] Nguyen Quoc Viet Hung, Huynh Huu Viet, Nguyen Thanh Tam, Weidlich Matthias, Yin Hongzhi, and Zhou Xiaofang. 2018. Computing crowd consensus with partial agreement. In 2018 IEEE 34th International Conference on Data Engineering (ICDE’18). 1749–1750. Google ScholarCross Ref
[36] Nguyen Thanh Tam, Duong Chi Thang, Weidlich Matthias, Yin Hongzhi, and Nguyen Quoc Viet Hung. 2017. Retaining data from streams of social platforms with minimal regret. In 26th International Joint Conference on Artificial Intelligence. 2850–2856.Google Scholar
[37] Rao Jinmeng, Gao Song, Li Mingxiao, and Huang Qunying. 2021. A privacy-preserving framework for location recommendation using decentralized collaborative machine learning. Transactions in GIS 25, 3 (2021), 1153–1175.Google ScholarCross Ref
[38] Rendle Steffen. 2012. Factorization machines with libFM. ACM Transactions on Intelligent Systems and Technology 3, 3 (2012), 1–22.Google ScholarDigital Library
[39] Robusto C.. 1957. The cosine-haversine formula. American Mathematical Monthly 64 (1957), 38.Google ScholarCross Ref
[40] Wang Qinyong, Yin Hongzhi, Chen Tong, Huang Zi, Wang Hao, Zhao Yanchang, and Hung Nguyen Quoc Viet. 2020. Next point-of-interest recommendation on resource-constrained mobile devices. In Proceedings of the Web Conference 2020 (WWW’20). ACM, 906–916.Google ScholarDigital Library
[41] Wang Qinyong, Yin Hongzhi, Chen Tong, Yu Junliang, Zhou Alexander, and Zhang Xiangliang. 2021. Fast-adapting and privacy-preserving federated recommender system. The International Journal on Very Large Data Bases (2021), 1–20.Google Scholar
[42] Wang Qinyong, Yin Hongzhi, Hu Zhiting, Lian Defu, Wang Hao, and Huang Zi. 2018. Neural memory streaming recommender networks with adversarial training. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2467–2475.Google ScholarDigital Library
[43] Wang Qinyong, Yin Hongzhi, Wang Hao, Nguyen Quoc Viet Hung, Huang Zi, and Cui Lizhen. 2019. Enhancing collaborative filtering with generative augmentation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 548–556.Google ScholarDigital Library
[44] Wang Xiwei, Nguyen Minh, Carr Jonathan, Cui Longyin, and Lim Kiho. 2020. A group preference-based privacy-preserving POI recommender system. Information & Communications Technology Express 6, 3 (2020), 204–208.Google Scholar
[45] Wei Kang, Li Jun, Ding Ming, Ma Chuan, Yang Howard H., Farokhi Farhad, Jin Shi, Quek Tony Q. S., and Poor H. Vincent. 2020. Federated learning with differential privacy: Algorithms and performance analysis. IEEE Transactions on Information Forensics and Security 15 (2020), 3454–3469.Google ScholarDigital Library
[46] Weimer Markus, Karatzoglou Alexandros, Le Quoc, and Smola Alex. 2007. Cofi rank-maximum margin matrix factorization for collaborative ranking. Advances in Neural Information Processing Systems 20 (2007), 1593–1600.Google Scholar
[47] Yao Di, Zhang Chao, Huang Jianhui, and Bi Jingping. 2017. Serm: A recurrent model for next location prediction in semantic trajectories. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 2411–2414.Google ScholarDigital Library
[48] Ye Guanhua, Yin Hongzhi, Chen Tong, Xu Miao, Nguyen Quoc Viet Hung, and Song Jiangning. 2022. Personalized on-device e-health analytics with decentralized block coordinate descent. IEEE Journal of Biomedical and Health Informatics 26, 6 (2022), 2778–2786.Google ScholarCross Ref
[49] Yu Junliang, Gao Min, Yin Hongzhi, Li Jundong, Gao Chongming, and Wang Qinyong. 2019. Generating reliable friends via adversarial training to improve social recommendation. In 2019 IEEE International Conference on Data Mining (ICDM’19). IEEE, 768–777.Google ScholarCross Ref
[50] Yu Junliang, Yin Hongzhi, Li Jundong, Gao Min, Huang Zi, and Cui Lizhen. 2020. Enhance social recommendation with adversarial graph convolutional networks. IEEE Transactions on Knowledge and Data Engineering 34 (2020), 3727–3739.Google Scholar
[51] Zhang Chen, Xie Yu, Bai Hang, Yu Bin, Li Weihong, and Gao Yuan. 2021. A survey on federated learning. Knowledge-Based Systems 216 (2021), 106775.Google ScholarCross Ref
[52] Zhao Kangzhi, Zhang Yong, Yin Hongzhi, Wang Jin, Zheng Kai, Zhou Xiaofang, and Xing Chunxiao. 2020. Discovering subsequence patterns for next POI recommendation. In IJCAI. 3216–3222.Google Scholar
[53] Zhao Pengpeng, Luo Anjing, Liu Yanchi, Zhuang Fuzhen, Xu Jiajie, Li Zhixu, Sheng Victor S., and Zhou Xiaofang. 2020. Where to go next: A spatio-temporal gated network for next POI recommendation. IEEE Transactions on Knowledge and Data Engineering 34, 5 (2020), 2512–2524. Google ScholarCross Ref
[54] Zhao Shenglin, Lyu Michael R., and King Irwin. 2018. STELLAR: Spatial-temporal latent ranking model for successive POI recommendation. In Point-of-Interest Recommendation in Location-Based Social Networks. Springer Singapore, Singapore, 79–94.Google ScholarCross Ref
[55] Zhou Kun, Wang Hui, Zhao Wayne Xin, Zhu Yutao, Wang Sirui, Zhang Fuzheng, Wang Zhongyuan, and Wen Ji-Rong. 2020. S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1893–1902.Google ScholarDigital Library

Index Terms

Decentralized Collaborative Learning Framework for Next POI Recommendation
1. Information systems
  1. Information retrieval
    1. Retrieval tasks and goals
      1. Recommender systems

Recommendations

Physical Trajectory Inference Attack and Defense in Decentralized POI Recommendation
WWW '24: Proceedings of the ACM on Web Conference 2024

As an indispensable personalized service within Location-Based Social Networks (LBSNs), the Point-of-Interest (POI) recommendation aims to assist individuals in discovering attractive and engaging places. However, the accurate recommendation capability ...
Read More
Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval

As an indispensable personalized service in Location-based Social Networks (LBSNs), the next Point-of-Interest (POI) recommendation aims to help people discover attractive and interesting places. Currently, most POI recommenders are based on the ...
Read More
POI recommendation through cross-region collaborative filtering

Recommending points of interest (POIs) to a user according to the user's current location and past check-in activities is the focus in this paper. Previously proposed probabilistic and topic model-based methods predict the POIs based on the distribution ...
Read More

Comments

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 Article

Published in
ACM Transactions on Information Systems Volume 41, Issue 3
July 2023
890 pages
ISSN:1046-8188
EISSN:1558-2868
DOI:10.1145/3582880
Editor:
Min Zhang
Tsinghua University, China
Issue’s Table of Contents
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 the author(s) 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
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
- Published: 7 February 2023
- Online AM: 8 August 2022
- Accepted: 29 July 2022
- Revised: 21 June 2022
- Received: 5 April 2022
Published in tois Volume 41, Issue 3

Permissions
Request permissions about this article.
Request Permissions

Check for updates
Author Tags
Point-of-Interest recommendation
decentralized collaborative learning
user privacy
Qualifiers
- research-article
- Refereed
Conference
Funding Sources
Other Metrics
View Article Metrics

Article Metrics
- 13
  Total Citations
  View Citations
- 1,127
  Total Downloads
- Downloads (Last 12 months)768
- Downloads (Last 6 weeks)86
Other Metrics
View Author Metrics
Cited By
View all

PDF Format

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Full Text

View this article in Full Text.

View Full Text

HTML Format

View this article in HTML Format .

View HTML Format

Decentralized Collaborative Learning Framework for Next POI Recommendation

ACM Transactions on Information Systems

Abstract

REFERENCES

Cited By

Index Terms

Recommendations

Physical Trajectory Inference Attack and Defense in Decentralized POI Recommendation

Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation

POI recommendation through cross-region collaborative filtering