Similarity-Promoting Resilient Adaptive Aggregation in Peer

Abstract Peer-to-peer collaborative learning offers a distributed approach that eliminates the risk of single-point-of-failures seen in federated learning. However, the presence of adversarial workers in the network, who aim to spread malicious information, presents a significant threat. Thus, ensuring the resilience of peer-to-peer learning emerges as a pivotal research objective. The challenge of safeguarding peer-to-peer learning against malicious attacks becomes even more difficult with non-convex loss functions and non-iid data distributions among the workers. This paper focuses on ensuring the robustness of distributed peer-to-peer learning in non-convex loss and non-iid data distribution scenario by using a resilient aggregation technique. This novel aggregation is designed by fostering similarity among the workers’ learning behaviors. Each worker aggregates the parameters of its neighbors as a weighted sum, where the weights are determined through an optimization problem aimed at learning the optimal parameters of each worker while protecting data privacy. The workers compute the loss using their neighbor’s models and individual private data, thus protecting data privacy. Theoretical analysis demonstrate that the normal workers’ parameters reach a consensus. Additionally, the difference between the parameters of normal workers and their respective optimal values remains bounded, with the bound being a function of few hyperparameters and the variance of non-iid data distribution among the workers. The effectiveness of the approach is evidenced by empirical evaluations performed on three machine learning classification tasks. The results demonstrate that the proposed adaptive aggregation method improves the test accuracy of the normal workers when compared to state-of-the-art aggregation techniques, under various adversarial scenarios spanning multiple attack models. Data Availability No datasets were generated or analysed during the current study. Notes The factor of 2/m is removed for brevity of the solution, without affecting the outcome of the optimization. The factor of 1/2 is introduced for simplification of solution. All proofs are included in the appendix. https://www.kaggle.com/datasets/hojjatk/mnist-dataset. https://archive.ics.uci.edu/ml/datasets/spambase. https://www.cs.toronto.edu/kriz/cifar.html. References Abou El Houda, Z., Moudoud, H., Brik, B., & Khoukhi, L. (2023). Securing federated learning through blockchain and explainable ai for robust intrusion detection in iot networks. In IEEE Infocom 2023-IEEE Conference on Computer Communications Workshops (INFOCOM Wkshps) (pp. 1–6). IEEE. Al-Huthaifi, R., Li, T., Huang, W., Gu, J., & Li, C. (2023). Federated learning in smart cities: Privacy and security survey. Information Sciences, 632, 833–857. Assran, M., Loizou, N., Ballas, N., & Rabbat, M. (2019). Stochastic gradient push for distributed deep learning. In International Conference on Machine Learning (pp. 344–353) PMLR. Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., & Shmatikov, V. (2020). How to backdoor federated learning. In International Conference on Artificial Intelligence and Statistics (pp. 2938–2948) PMLR. Balu, A., Jiang, Z., Tan, S.Y., Hedge, C., Lee, Y.M., Sarkar, S.: Decentralized deep learning using momentum-accelerated consensus. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3675–3679 (2021). IEEE Baruch, G., Baruch, M., & Goldberg, Y. (2019). A little is enough: Circumventing defenses for distributed learning. Advances in Neural Information Processing Systems. Bellet, A., Guerraoui, R., Taziki, M., & Tommasi, M. (2018). Personalized and private peer-to-peer machine learning. In International Conference on Artificial Intelligence and Statistics (pp. 473–481) PMLR. Bhagoji, A. N., Chakraborty, S., Mittal, P., & Calo, S. (2019). Analyzing federated learning through an adversarial lens. In International Conference on Machine Learning (pp. 634–643) PMLR. Bhowmick, C., Li, J., & Koutsoukos, X. (2023). Adaptive learning from peers for distributed actor-critic algorithms. In International Symposium on Distributed Computing and Artificial Intelligence (pp. 54–64). Springer. Biggio, B., Nelson, B., & Laskov, P. (2012). Poisoning attacks against support vector machines. arXiv preprint arXiv:1206.6389 Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017). Practical secure aggregation for privacy-preserving machine learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, (pp. 1175–1191). Bottou, L., Curtis, F. E., & Nocedal, J. (2018). Optimization methods for large-scale machine learning. SIAM Review, 60(2), 223–311. Chen, J.-H., Chen, M.-R., Zeng, G.-Q., & Weng, J.-S. (2021). Bdfl: a byzantine-fault-tolerance decentralized federated learning method for autonomous vehicle. IEEE Transactions on Vehicular Technology, 70(9), 8639–8652. Chen, X., Liu, C., Li, B., Lu, K., & Song, D. (2017). Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 Colin, I., Bellet, A., Salmon, J., & Clémençon, S. (2016). Gossip dual averaging for decentralized optimization of pairwise functions. In International Conference on Machine Learning (pp. 1388–1396) PMLR. Cui, Z., Xu, X., Fei, X., Cai, X., Cao, Y., Zhang, W., & Chen, J. (2020). Personalized recommendation system based on collaborative filtering for iot scenarios. IEEE Transactions on Services Computing, 13(4), 685–695. Dai, R., Shen, L., He, F., Tian, X., & Tao, D. (2022). Dispfl: Towards communication-efficient personalized federated learning via decentralized sparse training. arXiv preprint arXiv:2206.00187. Duchi, J. C., Agarwal, A., & Wainwright, M. J. (2011). Dual averaging for distributed optimization: Convergence analysis and network scaling. IEEE Transactions on Automatic control, 57(3), 592–606. El Hanjri, M., Kabbaj, H., Kobbane, A., & Abouaomar, A. (2023). Federated learning for water consumption forecasting in smart cities. In ICC 2023-IEEE International Conference on Communications (pp. 1798–1803). IEEE. Elgabli, A., Park, J., Bedi, A. S., Bennis, M., & Aggarwal, V. (2020). Gadmm: Fast and communication efficient framework for distributed machine learning. El-Mhamdi, E. M., Farhadkhani, S., Guerraoui, R., Guirguis, A., Hoang, L.-N., & Rouault, S. (2021). Collaborative learning in the jungle (decentralized, byzantine, heterogeneous, asynchronous and nonconvex learning). Advances in Neural Information Processing Systems, 34, 25044–25057. Fang, C., Yang, Z., & Bajwa, W. U. (2022). Bridge: Byzantine-resilient decentralized gradient descent. IEEE Transactions on Signal and Information Processing over Networks, 8, 610–626. Farhadkhani, S., Guerraoui, R., Gupta, N., Hoang, L.-N., Pinot, R., & Stephan, J. (2023). Robust collaborative learning with linear gradient overhead. In International Conference on Machine Learning (pp. 9761–9813) PMLR. Ghadimi, S., & Lan, G. (2013). Stochastic first-and zeroth-order methods for nonconvex stochastic programming. SIAM Journal on Optimization, 23(4), 2341–2368. Gorbunov, E., Borzunov, A., Diskin, M., & Ryabinin, M. (2022). Secure distributed training at scale. In International Conference on Machine Learning (pp. 7679–7739) PMLR. Guo, S., Zhang, T., Yu, H., Xie, X., Ma, L., Xiang, T., & Liu, Y. (2021). Byzantine-resilient decentralized stochastic gradient descent. IEEE Transactions on Circuits and Systems for Video Technology, 32(6), 4096–4106. Gupta, N., Doan, T. T., & Vaidya, N. H. (2021). Byzantine fault-tolerance in decentralized optimization under 2f-redundancy. In 2021 American Control Conference (ACC) (pp. 3632–3637). IEEE. He, L., Karimireddy, S. P., & Jaggi, M. (2022). Byzantine-robust decentralized learning via self-centered clipping. arXiv preprint arXiv:2202.01545. Ivannikova, E., Khan, S. A., Oyomno, W., Fu, Q., Tan, K. E., & Flanagan, A. (2019). Federated collaborative filtering for privacy-preserving personalized recommendation system. Corr. Jain, P., & Kar, P. (2017). Non-convex optimization for machine learning. Foundations Machine Learning, 10(3–4), 142–363. Jiang, J. C., Kantarci, B., Oktug, S., & Soyata, T. (2020). Federated learning in smart city sensing: Challenges and opportunities. Sensors, 20(21), 6230. Koloskova, A., Loizou, N., Boreiri, S., Jaggi, M., & Stich, S. (2020). A unified theory of decentralized sgd with changing topology and local updates. In International Conference on Machine Learning (pp. 5381–5393) PMLR. Konečnỳ, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016). Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492. Lalitha, A., Kilinc, O. C., Javidi, T., & Koushanfar, F. (2019). Peer-to-peer federated learning on graphs. arXiv preprint arXiv:1901.11173. Li, J., Abbas, W., & Koutsoukos, X. (2020a). Byzantine resilient distributed multi-task learning. Advances in Neural Information Processing Systems, 33, 18215–18225. Li, J., Lyu, L., Iso, D., Chakrabarti, C., & Spranger, M. (2022). Mocosfl: enabling cross-client collaborative self-supervised learning. The Eleventh International Conference on Learning Representations. Li, L., Fan, Y., Tse, M., & Lin, K.-Y. (2020b). A review of applications in federated learning. Computers & Industrial Engineering, 149, Article 106854. Li, L., Zhan, D.-C., & Li, X.-C. (2024). Aligning model outputs for class imbalanced non-iid federated learning. Machine Learning, 113(4), 1861–1884. Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020c). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60. Li, Z., Shi, W., & Yan, M. (2019). A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates. IEEE Transactions on Signal Processing, 67(17), 4494–4506. Lian, X., Zhang, C., Zhang, H., Hsieh, C.-J., Zhang, W., & Liu, J. (2017). Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent. Advances in Neural Information Processing Systems. Lian, X., Zhang, W., Zhang, C., & Liu, J. (2018). Asynchronous decentralized parallel stochastic gradient descent. In International Conference on Machine Learning, (pp. 3043–3052). PMLR Liang, F., Pan, W., & Ming, Z. (2021). Fedrec++: Lossless federated recommendation with explicit feedback. In Proceedings of the Aaai Conference on Artificial Intelligence, 35, 4224–4231. Lin, Y., Ren, P., Chen, Z., Ren, Z., Yu, D., Ma, J., Rijke, M. d., & Cheng, X. (2020). Meta matrix factorization for federated rating predictions. In Proceedings of the 43rd International ACM Sigir Conference on Research and Development in Information Retrieval, (pp. 981–990). Liu, Y., Ma, S., Aafer, Y., Lee, W.-C., Zhai, J., Wang, W., & Zhang, X. (2018). Trojaning attack on neural networks. In 25th Annual Network And Distributed System Security Symposium (NDSS 2018). Internet Soc. Liu, Y., Shi, Y., Li, Q., Wu, B., Wang, X., & Shen, L. (2024). Decentralized directed collaboration for personalized federated learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (pp. 23168–23178). McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics, (pp. 1273–1282). PMLR Mokhtari, A., & Ribeiro, A. (2016a). Decentralized double stochastic averaging gradient. In Signals, Systems and Computers, 2015 49th Asilomar Conference On, (pp. 406–410). Mokhtari, A., & Ribeiro, A. (2016b). Dsa: Decentralized double stochastic averaging gradient algorithm. The Journal of Machine Learning Research, 17(1), 2165–2199. Moulines, E., & Bach, F. (2011). Non-asymptotic analysis of stochastic approximation algorithms for machine learning. Advances in Neural Information Processing Systems. Mozaffari-Kermani, M., Sur-Kolay, S., Raghunathan, A., & Jha, N. K. (2014). Systematic poisoning attacks on and defenses for machine learning in healthcare. IEEE Journal of Biomedical and Health Informatics, 19(6), 1893–1905. Muñoz-González, L., Biggio, B., Demontis, A., Paudice, A., Wongrassamee, V., Lupu, E. C., & Roli, F. (2017). Towards poisoning of deep learning algorithms with back-gradient optimization. In Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security (pp. 27–38) Nedić, A., Olshevsky, A., & Rabbat, M. G. (2018). Network topology and communication-computation tradeoffs in decentralized optimization. Proceedings of the IEEE, 106(5), 953–976. Nedic, A., & Ozdaglar, A. (2009). Distributed subgradient methods for multi-agent optimization. IEEE Transactions on Automatic Control, 54(1), 48–61. Nguyen, A., Do, T., Tran, M., Nguyen, B.X., Duong, C., Phan, T., Tjiputra, E., Tran, Q.D.: Deep federated learning for autonomous driving. In 2022 IEEE Intelligent Vehicles Symposium (IV), pp. 1824–1830 (2022). IEEE Nguyen, D. C., Ding, M., Pathirana, P. N., Seneviratne, A., Li, J., & Poor, H. V. (2021). Federated learning for internet of things: A comprehensive survey. IEEE Communications Surveys & Tutorials, 23(3), 1622–1658. Peng, J., Li, W., & Ling, Q. (2021). Byzantine-robust decentralized stochastic optimization over static and time-varying networks. Signal Processing, 183, Article 108020. Pokhrel, S. R., & Choi, J. (2020). Federated learning with blockchain for autonomous vehicles: Analysis and design challenges. IEEE Transactions on Communications, 68(8), 4734–4746. Samarakoon, S., Bennis, M., Saad, W., & Debbah, M. (2018). Federated learning for ultra-reliable low-latency v2v communications. In 2018 IEEE Global Communications Conference (GLOBECOM) (pp. 1–7). IEEE. Schmidt, M., Le Roux, N., & Bach, F. (2017). Minimizing finite sums with the stochastic average gradient. Mathematical Programming, 162, 83–112. Schreyer, M., Sattarov, T., & Borth, D. (2022). Federated and privacy-preserving learning of accounting data in financial statement audits. In Proceedings of the Third ACM International Conference on AI in Finance, (pp. 105–113). Seng, K. P., Ang, L. M., & Ngharamike, E. (2022). Artificial intelligence internet of things: A new paradigm of distributed sensor networks. International Journal of Distributed Sensor Networks, 18(3), 15501477211062836. Shayan, M., Fung, C., Yoon, C. J., & Beschastnikh, I. (2020). Biscotti: A blockchain system for private and secure federated learning. IEEE Transactions on Parallel and Distributed Systems, 32(7), 1513–1525. Shen, L., Tang, Z., Wu, L., Zhang, Y., Chu, X., Qin, T., & Han, B. (2025). Hot-pluggable federated learning: Bridging general and personalized fl via dynamic selection. The Thirteenth International Conference on Learning Representations. Shi, W., Ling, Q., Wu, G., & Yin, W. (2015a). Extra: An exact first-order algorithm for decentralized consensus optimization. SIAM Journal on Optimization, 25(2), 944–966. Shi, W., Ling, Q., Wu, G., & Yin, W. (2015b). A proximal gradient algorithm for decentralized composite optimization. IEEE Transactions on Signal Processing, 63(22), 6013–6023. Shi, W., Ling, Q., Yuan, K., Wu, G., & Yin, W. (2014). On the linear convergence of the admm in decentralized consensus optimization. IEEE Transactions on Signal Processing, 62(7), 1750–1761. Su, L., & Vaidya, N. (2015). Byzantine multi-agent optimization: Part i. arXiv preprint arXiv:1506.04681. Tang, H., Lian, X., Yan, M., Zhang, C., & Liu, J. (2018). \(d^2\): Decentralized training over decentralized data. In International Conference on Machine Learning (pp. 4848–4856) PMLR. Tang, Z., Shi, S., Li, B., & Chu, X. (2022). Gossipfl: A decentralized federated learning framework with sparsified and adaptive communication. IEEE Transactions on Parallel and Distributed Systems, 34(3), 909–922. Terrail, J. O. D., Ayed, S.-S., Cyffers, E., Grimberg, F., He, C., Loeb, R., Mangold, P., Marchand, T., Marfoq, O., & Mushtaq, E. (2022). Flamby: Datasets and benchmarks for cross-silo federated learning in realistic healthcare settings. arXivpreprint arXiv:2210.04620. Vanhaesebrouck, P., Bellet, A., & Tommasi, M. (2017). Decentralized collaborative learning of personalized models over networks. In Artificial Intelligence and Statistics (pp. 509–517) PMLR. WeBank: Webank and swiss re signed cooperation mou (2019) Wu, J., Liu, Q., Huang, Z., Ning, Y., Wang, H., Chen, E., Yi, J., & Zhou, B. (2021). Hierarchical personalized federated learning for user modeling. In Proceedings of the Web Conference, 2021, 957–968. Xiao, L., & Boyd, S. (2004). Fast linear iterations for distributed averaging. Systems & Control Letters, 53(1), 65–78. Xie, C., Koyejo, O., & Gupta, I. (2020). Fall of empires: Breaking byzantine-tolerant sgd by inner product manipulation. In Uncertainty in Artificial Intelligence (pp. 261–270) PMLR. Yang, C., & Ghaderi, J. (2024). Byzantine-robust decentralized learning via remove-then-clip aggregation. In Proceedings of the AAAI Conference on Artificial Intelligence, 38, 21735–21743. Yang, Z., & Bajwa, W. U. (2019). Byrdie: Byzantine-resilient distributed coordinate descent for decentralized learning. IEEE Transactions on Signal and Information Processing over Networks, 5(4), 611–627. Yuan, K., Ling, Q., & Yin, W. (2016). On the convergence of decentralized gradient descent. SIAM Journal on Optimization, 26(3), 1835–1854. Yuan, K., Ying, B., Zhao, X., & Sayed, A. H. (2018). Exact diffusion for distributed optimization and learning–part i: Algorithm development. IEEE Transactions on Signal Processing, 67(3), 708–723. Yuan, L., Wang, Z., Sun, L., Yu, P. S., & Brinton, C. G. (2024). Decentralized federated learning: A survey and perspective. IEEE Internet of Things Journal, 11(21), 34617–34638. Zhang, H., Bosch, J., & Olsson, H. H. (2021). Real-time end-to-end federated learning: An automotive case study. In 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC) (pp. 459–468). IEEE. Author information Authors and Affiliations Contributions C.B. developed the core methodology, implemented the algorithms, performed the theoretical analysis, and performed the experiments. C.B. and X.K. analyzed the results and interpreted the findings. C.B. wrote the main manuscript draft. X.K. provided supervision, conceptual guidance, and critical revisions. All authors reviewed and approved the final manuscript. Corresponding author Ethics declarations Conflict of interest The authors declare no conflict of interest. Additional information Editor: Bo Han. Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Supplementary Information Below is the link to the electronic supplementary material. Rights and permissions Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. About this article Cite this article Bhowmick, C., Koutsoukos, X. Similarity-Promoting Resilient Adaptive Aggregation in Peer-to-Peer Machine Learning. Mach Learn 115, 223 (2026). https://doi.org/10.1007/s10994-026-07162-3 Received: Revised: Accepted: Published: Version of record: DOI: https://doi.org/10.1007/s10994-026-07162-3