{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T20:35:43Z","timestamp":1761165343439,"version":"build-2065373602"},"reference-count":29,"publisher":"Sociedade Brasileira de Computa\u00e7\u00e3o - SBC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Este trabalho prop\u00f5e uma nova estrat\u00e9gia de Aprendizado Federado para Ranqueamento (FL2R) em cen\u00e1rios com dados n\u00e3o independentes e n\u00e3o identicamente distribu\u00eddos (n\u00e3o-IID) entre clientes. Apresentamos o FedRisk, um m\u00e9todo de agrega\u00e7\u00e3o sens\u00edvel ao risco que pondera as contribui\u00e7\u00f5es dos clientes conforme sua confiabilidade, aliado a um mecanismo de reutiliza\u00e7\u00e3o de par\u00e2metros do modelo global anterior, para mitigar os efeitos da heterogeneidade dos dados. Experimentos com o conjunto MSLR-WEB10K mostram que o FedRisk supera o FedProx \u2014 baseline mais robusto \u2014 ao reduzir a diferen\u00e7a de desempenho entre modelos federados e centralizados. O FedRisk alcan\u00e7ou uma melhoria de 15.6% no nDCG@5 em rela\u00e7\u00e3o ao FedProx e reduziu substancialmente a vari\u00e2ncia, aumentando a estabilidade entre rodadas. Al\u00e9m disso, para m\u00e9tricas como nDCG@10, o FedRisk igualou o desempenho do modelo centralizado \u2014 feito in\u00e9dito entre os m\u00e9todos comparados, sobretudo em um cen\u00e1rio federado n\u00e3o-IID.<\/jats:p>","DOI":"10.5753\/sbbd.2025.246990","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T19:26:36Z","timestamp":1761074796000},"page":"1-14","source":"Crossref","is-referenced-by-count":0,"title":["Aprendizado Federado Incremental e Sens\u00edvel ao Risco para Modelos de Ranqueamento em Cen\u00e1rios com Distribui\u00e7\u00f5es Heterog\u00eaneas de Dados"],"prefix":"10.5753","author":[{"given":"Gestefane","family":"Rabbi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Celso","family":"Fran\u00e7a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel Xavier de","family":"Sousa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thierson Couto","family":"Rosa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9142-2919","authenticated-orcid":false,"given":"Jussara M.","family":"Almeida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos Andr\u00e9","family":"Gon\u00e7alves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3742","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"Ads, Z. et al. (2024). Risk-aware accelerated federated learning over heterogeneous wireless networks. arXiv preprint arXiv:2401.09267.","DOI":"10.1109\/ICC51166.2024.10622824"},{"key":"2","unstructured":"Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Kwing, H. L., Parcollet, T., Gusm\u00e3o, P. P. d., and Lane, N. D. (2020). Flower: A friendly federated learning research framework. arXiv preprint arXiv:2007.14390."},{"key":"3","doi-asserted-by":"crossref","unstructured":"Bottou, L. (2010). Large-scale machine learning with stochastic gradient descent. In Proceedings of COMPSTAT\u20192010, pages 177\u2013186. Springer.","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"4","unstructured":"Brownlee, J. (2018). Statistical Methods for Machine Learning. Machine Learning Mastery."},{"key":"5","unstructured":"Chen, S. et al. (2021). Risk-aware federated learning in crowdsensing systems. arXiv preprint arXiv:2101.01266."},{"key":"6","doi-asserted-by":"crossref","unstructured":"Dincer, B., Zhu, Y., Craswell, N., and Zhang, M. (2016). Risk-sensitive evaluation and learning to rank using multiple baselines. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, pages 483\u2013492.","DOI":"10.1145\/2911451.2911511"},{"key":"7","unstructured":"Divi, S., Lin, Y.-S., Farrukh, H., and Celik, Z. B. (2021). New metrics to evaluate the performance and fairness of personalized federated learning."},{"key":"8","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"9","unstructured":"Hejazinia, M. et al. (2022). Fel: High capacity learning for recommendation and ranking via federated ensemble learning. arXiv preprint arXiv:2206.03852."},{"key":"10","doi-asserted-by":"crossref","unstructured":"J\u00e4rvelin, K. and Kek\u00e4l\u00e4inen, J. (2002). Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422\u2013446.","DOI":"10.1145\/582415.582418"},{"key":"11","unstructured":"Jeong, J., Kim, H., Park, J., Lee, S., and Yoon, D. N. (2022). Fedcc: Boosting robustness of federated learning against model poisoning attacks. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (CCS), pages 861\u2013875. ACM."},{"key":"12","doi-asserted-by":"crossref","unstructured":"Jiang, J. C., Kantarci, B., Oktug, S., and Soyata, T. (2020). Federated learning in smart city sensing: Challenges and opportunities. Sensors, 20(21):6230.","DOI":"10.3390\/s20216230"},{"key":"13","unstructured":"Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S., Stich, S. U., and Suresh, A. T. (2020). Scaffold: Stochastic controlled averaging for federated learning. In International Conference on Machine Learning (ICML)."},{"key":"14","doi-asserted-by":"crossref","unstructured":"K\u00f6ppel, M., Segner, A., Wagener, M., Pensel, L., Karwath, A., and Kramer, S. (2019). Pairwise learning to rank by neural networks revisited: Reconstruction, theoretical analysis and practical performance. arXiv preprint arXiv:1909.02768.","DOI":"10.1007\/978-3-030-46133-1_15"},{"key":"15","unstructured":"Li, T., Sahu, A. K., Talwalkar, A., and Smith, V. (2020). Federated optimization in heterogeneous networks. In Proceedings of Machine Learning and Systems, pages 429\u2013450."},{"key":"16","unstructured":"Liu, S., Celik, E., and Widmer, J. (2021). Label-aware aggregation for improved federated learning. In Proceedings of the 2021 20th ACM\/IEEE International Conference on Information Processing in Sensor Networks (IPSN), pages 1\u201313. IEEE."},{"key":"17","unstructured":"Neto, H. N. C., Mattos, D. M. F., and Fernandes, N. C. (2020). Privacidade do usu\u00e1rio em aprendizado colaborativo: Federated learning, da teoria \u00e0 pr\u00e1tica. In Simp\u00f3sio Brasileiro de Seguran\u00e7a da Informa\u00e7\u00e3o e de Sistemas Computacionais (SBSEG)."},{"key":"18","unstructured":"Qin, T. and Liu, T. (2013). Introducing LETOR 4.0 datasets. CoRR, abs\/1306.2597."},{"key":"19","doi-asserted-by":"crossref","unstructured":"Rodrigues, P. H. S., de Sousa, D. X., Fran\u00e7a, C., Rabbi, G., Couto Rosa, T., and Gon\u00e7alves, M. A. (2025). Risk-sensitive optimization of neural deep learning ranking models with applications in ad-hoc retrieval and recommender systems. Information Processing & Management, 62(4):104126.","DOI":"10.1016\/j.ipm.2025.104126"},{"key":"20","doi-asserted-by":"crossref","unstructured":"Rodrigues, P. H. S., Xavier Sousa, D., Couto Rosa, T., and Gon\u00e7alves, M. A. (2022). Risk-sensitive deep neural learning to rank. In ACM SIGIR Conference, SIGIR \u201922, page 803\u2013813.","DOI":"10.1145\/3477495.3532056"},{"key":"21","unstructured":"Spiegelhalter, D. (2024). The Art of Uncertainty: How to Navigate Chance, Ignorance, Risk and Luck. Pelican Books."},{"key":"22","unstructured":"Tong, Y. et al. (2021). An efficient approach for cross-silo federated learning to rank. In Proceedings of the IEEE International Conference on Data Engineering (ICDE)."},{"key":"23","doi-asserted-by":"crossref","unstructured":"Voorhees, E. M. (1999). The trec-8 question answering track report. In Proceedings of the Eighth Text Retrieval Conference (TREC-8). National Institute of Standards and Technology (NIST).","DOI":"10.6028\/NIST.SP.500-246.overview-overview"},{"key":"24","doi-asserted-by":"crossref","unstructured":"Voorhees, E. M. et al. (1999). The trec-8 question answering track report. In TREC, volume 8.","DOI":"10.6028\/NIST.SP.500-246.qa-overview"},{"key":"25","unstructured":"Wang, J. and Liu, M. (2020). Tackling the objective inconsistency problem in heterogeneous federated optimization. In NeurIPS."},{"key":"26","doi-asserted-by":"crossref","unstructured":"Wang, L., Bennett, P. N., and Collins-Thompson, K. (2012). Robust ranking models via risk-sensitive optimization. In Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201912, page 761\u2013770, New York, NY, USA. Association for Computing Machinery.","DOI":"10.1145\/2348283.2348385"},{"key":"27","doi-asserted-by":"crossref","unstructured":"Wang, S. and Zuccon, G. (2022). Is non-iid data a threat in federated online learning to rank? In ACM SIGIR Conference, SIGIR \u201922, page 2801\u20132813.","DOI":"10.1145\/3477495.3531709"},{"key":"28","unstructured":"Wang, Y., Li, T.-Y., Wang, D., and Zhu, M. (2013). A theoretical analysis of ndcg type ranking measures. Journal of Machine Learning Research, 14:25\u201354."},{"key":"29","unstructured":"Zhao, S. et al. (2024). Federated risk-aware learning with central sensitivity estimation. arXiv preprint arXiv:2502.17694."}],"event":{"name":"Simp\u00f3sio Brasileiro de Banco de Dados","number":"40","location":"Brasil","acronym":"SBBD 2025"},"container-title":["Anais do XL Simp\u00f3sio Brasileiro de Banco de Dados (SBBD 2025)"],"original-title":[],"link":[{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/download\/37224\/37007","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/download\/37224\/37007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T19:32:42Z","timestamp":1761075162000},"score":1,"resource":{"primary":{"URL":"https:\/\/sol.sbc.org.br\/index.php\/sbbd\/article\/view\/37224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":29,"URL":"https:\/\/doi.org\/10.5753\/sbbd.2025.246990","relation":{},"subject":[],"published":{"date-parts":[[2025,9,29]]}}}