Skip to main content
SpringerLink
Log in

User-controlled federated matrix factorization for recommender systems

  • Published:
Journal of Intelligent Information Systems Aims and scope Submit manuscript

Abstract

Recommendation services have been extensively adopted in various user-centered applications to help users navigate a vast space of possible choices. In such scenarios, data ownership is a crucial concern since users may not be willing to share their sensitive preferences (e.g., visited locations, read books, bought items) with a central server. Unfortunately, data collection is at the basis of modern approaches to the recommendation problem. Decreased users’ willingness to share personal information and data protection policies can result in the “data scarcity” dilemma affecting applications such as recommender systems. In the work at hand, we thoroughly study and extend FPL (Federated Pair-wise Learning), a recommendation approach that follows the Federated Learning principles. In FPL, users collaborate in training a pair-wise learning to rank factorization model while controlling the amount of sensitive data that leaves their devices. An extensive experimental evaluation reveals the effectiveness of the proposed architecture concerning the accuracy and beyond-accuracy objectives and the impact of disclosed users’ information on the quality of the final model. The paper also analyzes the impact of communication costs with the central server on the system’s performance by varying local computation and training parallelism. Furthermore, the study investigates the injection of additional biases in the final recommendation that could affect the fairness of the system. The public implementation is available at https://split.to/sisinflab-fpl.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. The limitations of the Collaborative Filtering in a cold-start user setting are well-known in literature. However, they are beyond the scope of this work.

  2. Since no source code is available, we implemented it from scratch and considered it in the reader’s interest.

  3. http://www.mymedialite.net/

  4. https://split.to/sisinflab-fpl

  5. The complete results are available in the implementation repository.

References

  • Abadi, M, Chu, A, Goodfellow, IJ, McMahan, HB, Mironov, I, Talwar, K, & Zhang, L (2016). Deep learning with differential privacy. In E R Weippl, S Katzenbeisser, C Kruegel, A C Myers, & S Halevi (Eds.) Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (pp. 308–318). Vienna: ACM. https://doi.org/10.1145/2976749.2978318.

  • Adomavicius, G, & Kwon, Y (2012). Improving aggregate recommendation diversity using ranking-based techniques. IEEE TKDE, 24(5), 896–911.

    Google Scholar 

  • Adomavicius, G, & Zhang, J (2012). Impact of data characteristics on recommender systems performance. ACM Trans Manag Inf Syst, 3(1), 3:1–3:17. https://doi.org/10.1145/2151163.2151166.

    Article  Google Scholar 

  • Ammad-ud-din, M, Ivannikova, E, Khan, SA, Oyomno, W, Fu, Q, Tan, KE, & Flanagan, A. (2019). Federated collaborative filtering for privacy-preserving personalized recommendation system. CoRR arXiv:1901.09888.

  • Anelli, VW, Bellogín, A, Ferrara, A, Malitesta, D, Merra, FA, Pomo, C, Donini, FM, & Noia, TD. (2021). Elliot: A comprehensive and rigorous framework for reproducible recommender systems evaluation. In: SIGIR. ACM, pp 2405–2414.

  • Anelli, VW, Deldjoo, Y, Di Noia, T, & Ferrara, A. (2019). Towards effective device-aware federated learning. In: Int. Conf. of the Italian Association for Artificial Intelligence. Springer, pp 477–491.

  • Anelli, VW, Deldjoo, Y, Noia, TD, & Ferrara, A (2020). Prioritized multi-criteria federated learning. Intell Artif, 14(2), 183–200.

    Google Scholar 

  • Anelli, VW, Deldjoo, Y, Noia, TD, Ferrara, A, & Narducci, F. (2021). Federank: User controlled feedback with federated recommender systems. In: ECIR (1), Lecture Notes in Computer Science, vol 12656. Springer, pp 32–47.

  • Anelli, VW, Deldjoo, Y, Noia, TD, Ferrara, A, & Narducci, F. (2021). How to put users in control of their data in federated top-n recommendation with learning to rank. In: SAC ’21: The 36th ACM/SIGAPP symposium on applied computing, virtual event. ACM, Republic of Korea, pp 1359–1362. https://doi.org/10.1145/3412841.3442010.

  • Anelli, VW, Noia, TD, Lops, P, & Sciascio, ED (2017). Feature factorization for top-n recommendation: From item rating to features relevance. In RecSysKTL, CEUR Workshop Proceedings, (Vol. 1887 pp. 16–21). CEUR-WS.org.

  • Anelli, VW, Noia, TD, Sciascio, ED, Ferrara, A, & Mancino, ACM (2021). Sparse feature factorization for recommender systems with knowledge graphs. In RecSys 2021: Fifteenth ACM Conference on Recommender Systems (RecSys ’21). Amsterdam: ACM. https://doi.org/10.1145/3460231.3474243.

  • Anelli, VW, Noia, TD, Sciascio, ED, Pomo, C, & Ragone, A (2019). On the discriminative power of hyper-parameters in cross-validation and how to choose them. In Proc. of the 13th ACM Conf. on Recommender Systems (pp. 447–451).

  • Anelli, VW, Noia, TD, Sciascio, ED, Ragone, A, & Trotta, J (2019). How to make latent factors interpretable by feeding factorization machines with knowledge graphs. In ISWC (1), Lecture Notes in Computer Science, (Vol. 11778 pp. 38–56). Springer.

  • Anelli, VW, Noia, TD, Sciascio, ED, Ragone, A, & Trotta, J (2019). Local popularity and time in top-n recommendation. In European Conf. on Information Retrieval, (Vol. 11437 pp. 861–868). Springer.

  • Bilge, A, Kaleli, C, Yakut, I, Gunes, I, & Polat, H (2013). A survey of privacy-preserving collaborative filtering schemes. Int J Softw Eng Knowl Eng, 23(8), 1085–1108.

    Article  Google Scholar 

  • Bonawitz, K, Ivanov, V, Kreuter, B, Marcedone, A, McMahan, HB, Patel, S, Ramage, D, Segal, A, & Seth, K (2017). Practical secure aggregation for privacy preserving machine learning. IACR Cryptol ePrint Arch, 2017, 281. http://eprint.iacr.org/2017/281.

    Google Scholar 

  • Bozdag, E (2013). Bias in algorithmic filtering and personalization. Ethics Inf Technol, 15 (3), 209–227. https://doi.org/10.1007/s10676-013-9321-6.

    Article  Google Scholar 

  • Burke, R, Sonboli, N, Mansoury, M, & Ordo nez-Gauger, A. (2017). Balanced neighborhoods for fairness-aware collaborative recommendation.

  • Castells, P, Hurley, NJ, & Vargas, S (2015). Novelty and diversity in recommender systems. Springer.

    Book  Google Scholar 

  • Chai, D, Wang, L, Chen, K, & Yang, Q. (5555aug). Secure federated matrix factorization. IEEE Intell Syst, 01, 1–1. https://doi.org/10.1109/MIS.2020.3014880.

  • Chai, D, Wang, L, Chen, K, & Yang, Q. (2019). Secure federated matrix factorization. CoRR arXiv:1906.05108.

  • Dacrema, MF, Cremonesi, P, & Jannach, D (2019). Are we really making much progress? A worrying analysis of recent neural recommendation approaches. In T Bogers, A Said, P Brusilovsky, & D Tikk (Eds.) Proceedings of the 13th ACM Conference on Recommender Systems, RecSys 2019 (pp. 101–109). Copenhagen: ACM. https://doi.org/10.1145/3298689.3347058.

  • Deldjoo, Y, Anelli, VW, Zamani, H, Bellogín, A, & Noia, TD (2021). A flexible framework for evaluating user and item fairness in recommender systems. User Model User Adapt Interact, 31(3), 457–511. https://doi.org/10.1007/s11257-020-09285-1.

    Article  Google Scholar 

  • Duriakova, E, Tragos, EZ, Smyth, B, Hurley, N, Pe na, F J, Symeonidis, P, Geraci, J, & Lawlor, A (2019). Pdmfrec: a decentralised matrix factorisation with tunable user-centric privacy. In Proc. of the 13th ACM Conf. on Recommender Systems, RecSys 2019 (pp. 457–461). Copenhagen.

  • Dwork, C, Hardt, M, Pitassi, T, Reingold, O, & Zemel, RS. (2011). Fairness through awareness. CoRR arXiv:1104.3913.

  • Fierimonte, R, Scardapane, S, Uncini, A, & Panella, M (2017). Fully decentralized semi-supervised learning via privacy-preserving matrix completion. IEEE Trans Neural Netw Learn Syst, 28(11), 2699–2711. https://doi.org/10.1109/TNNLS.2016.2597444.

    Article  MathSciNet  Google Scholar 

  • General data protection regulation. (2020). (accessed May 31, 2020). https://gdpr-info.eu/.

  • Gunawardana, A, & Shani, G (2015). Evaluating recommender systems. In Recommender Systems Handbook (pp. 265–308). Springer.

  • Guo, Y, Liu, F, Cai, Z, Zeng, H, Chen, L, Zhou, T, & Xiao, N (2021). PREFER: point-of-interest recommendation with efficiency and privacy-preservation via federated edge learning. Proc ACM Interact Mob Wearable Ubiquit Technol, 5(1), 13:1–13:25. https://doi.org/10.1145/3448099.

    Article  Google Scholar 

  • Han, J, Ma, Y, Mei, Q, & Liu, X (2021). Deeprec: On-device deep learning for privacy-preserving sequential recommendation in mobile commerce. In J Leskovec, M Grobelnik, M Najork, J Tang, & L Zia (Eds.) WWW ’21: The web conference 2021, virtual event / ljubljana(pp. 900–911). Slovenia: ACM / IW3C2. https://doi.org/10.1145/3442381.3449942.

  • Hu, Y, Koren, Y, & Volinsky, C (2008). Collaborative filtering for implicit feedback datasets. In Proc. of the 8th IEEE Int. Conf. on Data Mining (ICDM 2008) (pp. 263–272). Pisa: IEEE Computer Society.

  • Huang, Z, Chen, H, & Zeng, DD (2004). Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering. ACM Trans Inf Syst, 22(1), 116–142.

    Article  Google Scholar 

  • Jalalirad, A, Scavuzzo, M, Capota, C, & Sprague, MR (2019). A simple and efficient federated recommender system. In Proc. of the 6th IEEE/ACM Int. Conf. on Big Data Computing, Applications and Technologies (pp. 53–58). https://doi.org/10.1145/3365109.3368788.

  • Jeckmans, AJP, Beye, M, Erkin, Z, Hartel, PH, Lagendijk, RL, & Tang, Q (2013). Privacy in recommender systems. In Social Media Retrieval, Computer Communications and Networks (pp. 263–281). Springer.

  • Kairouz, P, McMahan, HB, Avent, B, Bellet, A, Bennis, M, Bhagoji, AN, Bonawitz, K, Charles, Z, Cormode, G, Cummings, R, & et al. (2019). Advances and open problems in federated learning. arXiv:1912.04977.

  • Kairouz, P, McMahan, HB, Avent, B, Bellet, A, Bennis, M, Bhagoji, AN, Bonawitz, KA, Charles, Z, Cormode, G, Cummings, R, D’Oliveira, RGL, Rouayheb, SE, Evans, D, Gardner, J, Garrett, Z, Gascón, A, Ghazi, B, Gibbons, PB, Gruteser, M, ..., Zhao, S. (2019). Advances and open problems in federated learning. arXiv:https://arxiv.org/abs/1912.04977.

  • Kharitonov, E (2019). Federated online learning to rank with evolution strategies. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (pp. 249–257).

  • Konecný, J, McMahan, B, & Ramage, D. (2015). Federated optimization: Distributed optimization beyond the datacenter. CoRR arXiv:1511.03575.

  • Konecný, J, McMahan, HB, Ramage, D, & Richtárik, P. (2016). Federated optimization: Distributed machine learning for on-device intelligence. CoRR arXiv:1610.02527.

  • Koren, Y (2008). Factorization meets the neighborhood: a multifaceted collaborative filtering model. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 426–434). Las Vegas. https://doi.org/10.1145/1401890.1401944.

  • Koren, Y (2010). Factor in the neighbors: Scalable and accurate collaborative filtering. ACM Trans Knowl Discov Data (TKDD), 4(1), 1–24.

    Article  Google Scholar 

  • Koren, Y, Bell, RM, & Volinsky, C (2009). Matrix factorization techniques for recommender systems. IEEE Comput, 42(8), 30–37.

    Article  Google Scholar 

  • Koren, Y, & Sill, J (2011). Ordrec: an ordinal model for predicting personalized item rating distributions. In B Mobasher, R D Burke, D Jannach, & G Adomavicius (Eds.) Proc. of the 2011 ACM Conf. on Recommender Systems, RecSys 2011 (pp. 117–124). Chicago: ACM.

  • kumar Bokde, D, Girase, S, & Mukhopadhyay, D. (2015). Role of matrix factorization model in collaborative filtering algorithm: A survey. CoRR arXiv:1503.07475.

  • Li, X, Huang, K, Yang, W, Wang, S, & Zhang, Z (2020). On the convergence of fedavg on non-iid data. In 8th International Conference on Learning Representations, ICLR 2020. https://openreview.net/forum?id=HJxNAnVtDS. Addis Ababa: OpenReview.net.

  • Liang, D, Krishnan, RG, Hoffman, MD, & Jebara, T (2018). Variational autoencoders for collaborative filtering. In Proceedings of 2018 WWW Conference (pp. 689–698).

  • Mansoury, M, Mobasher, B, Burke, R, & Pechenizkiy, M (2019). Bias disparity in collaborative recommendation: Algorithmic evaluation and comparison. In R Burke, H Abdollahpouri, E C Malthouse, K P Thai, & Y Zhang (Eds.) Proceedings of the Workshop on Recommendation in Multi-stakeholder Environments co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019), CEUR Workshop Proceedings, Vol. 2440. Copenhagen: CEUR-WS.org. http://ceur-ws.org/Vol-2440/paper6.pdf.

  • McFee, B, Barrington, L, & Lanckriet, GRG (2012). Learning content similarity for music recommendation. IEEE Trans Audio Speech Lang Process, 20 (8), 2207–2218.

    Article  Google Scholar 

  • McMahan, B, Moore, E, Ramage, D, Hampson, S, & y Arcas, BA (2017). Communication-efficient learning of deep networks from decentralized data. In Proc. of 20th Int. Conf. on Artificial Intelligence and Stat. (pp. 1273–1282) http://proceedings.mlr.press/v54/mcmahan17a.html.

  • McNee, SM, Riedl, J, & Konstan, JA (2006). Being accurate is not enough: how accuracy metrics have hurt recommender systems. In CHI’06 extended abstracts on Human factors in computing systems (pp. 1097–1101).

  • Mesas, RM, & Bellogín, A (2017). Evaluating decision-aware recommender systems. In Proc. of the 11th ACM Conf. on Recommender Systems (pp. 74–78). https://doi.org/10.1145/3109859.3109888.

  • Rendle, S (2010). Factorization machines. In ICDM 2010, the 10th IEEE international conference on data mining (pp. 995–1000). Sydney. https://doi.org/10.1109/ICDM.2010.127.

  • Rendle, S, Freudenthaler, C, Gantner, Z, & Schmidt-Thieme, L (2009). BPR: bayesian personalized ranking from implicit feedback. In Proc. of the 25th Conf. on Uncertainty in Artificial Intelligence (pp. 452–461).

  • Rendle, S, Freudenthaler, C, & Schmidt-Thieme, L (2010). Factorizing personalized markov chains for next-basket recommendation. In Proceedings of the 19th International Conference on World Wide Web, WWW 2010 (pp. 811–820). Raleigh. https://doi.org/10.1145/1772690.1772773.

  • Rendle, S, & Schmidt-Thieme, L (2010). Pairwise interaction tensor factorization for personalized tag recommendation. In Proceedings of the Third International Conference on Web Search and Web Data Mining, WSDM 2010 (pp. 81–90). New York. https://doi.org/10.1145/1718487.1718498.

  • Shi, Y, Larson, M, & Hanjalic, A (2010). List-wise learning to rank with matrix factorization for collaborative filtering. In Proceedings of the fourth ACM conference on Recommender systems (pp. 269–272).

  • Yang, D, Zhang, D, & Qu, B (2016). Participatory cultural mapping based on collective behavior data in location-based social networks. ACM TIST, 7 (3), 30:1–30:23.

    Google Scholar 

  • Yang, Q, Liu, Y, Chen, T, & Tong, Y (2019). Federated machine learning: Concept and applications. ACM TIST, 10(2), 12:1–12:19.

    Google Scholar 

  • Yang, Q, Liu, Y, Cheng, Y, Kang, Y, Chen, T, & Yu, H. (2019). Federated learning. Morgan & Claypool Publishers.

  • Yuan, J, Shalaby, W, Korayem, M, Lin, D, AlJadda, K, & Luo, J (2016). Solving cold-start problem in large-scale recommendation engines: A deep learning approach. In 2016 IEEE Int. Conf. on Big Data, BigData 2016 (pp. 1901–1910). Washington: IEEE Computer Society.

  • Zhao, Y, Li, M, Lai, L, Suda, N, Civin, D, & Chandra, V. (2018). Federated learning with non-iid data. CoRR arXiv:1806.00582.

Download references

Author information

Authors and Affiliations

  1. Politecnico di Bari, Bari, Italy

    Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Antonio Ferrara & Fedelucio Narducci

Authors
  1. Vito Walter Anelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yashar Deldjoo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tommaso Di Noia
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Antonio Ferrara
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Fedelucio Narducci
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Antonio Ferrara.

Ethics declarations

Competing interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Anelli, V.W., Deldjoo, Y., Di Noia, T. et al. User-controlled federated matrix factorization for recommender systems. J Intell Inf Syst 58, 287–309 (2022). https://doi.org/10.1007/s10844-021-00688-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10844-021-00688-z

Keywords

Search

Navigation