Federated Learning for Supply Chain

Federated learning (FL) is a machine learning paradigm that allows multiple parties to collaboratively train a shared model without exchanging their raw training data. Instead, each participant trains a local model on their own data and shares only model updates (gradients or parameters) with a central aggregator—or, in decentralised variants, directly with peers. This preserves data locality, confidentiality, and regulatory compliance while enabling collective intelligence to emerge from distributed datasets.

In supply chain contexts, federated learning is particularly compelling. Modern supply chains involve dozens or hundreds of firms—buyers, suppliers, logistics providers, financial institutions—each holding operationally sensitive data. Pooling this data centrally is often impossible due to competitive concerns, data protection regulations (e.g., GDPR), and contractual restrictions. Federated learning unlocks the ability to train powerful shared models for demand forecasting, anomaly detection, supplier risk assessment, and collaborative inventory management without any party surrendering proprietary information.

Research in this area addresses key technical challenges including statistical heterogeneity across partners (non-IID data), communication efficiency, robustness to adversarial participants, and privacy guarantees via differential privacy or secure multi-party computation. Contributions from the Supply Chain AI Lab at the University of Cambridge and the broader machine learning community are establishing the foundations for trustworthy, cross-enterprise AI in supply chains.

We invite you to explore the curated collection of key publications below, offering a gateway into this promising field.

List of Publications

1. McMahan, B., Moore, E., Ramage, D., Hampson, S. and y Arcas, B.A., 2017. Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), pp.1273-1282. [PDF]
2. Kairouz, P., McMahan, H.B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A.N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R. and D'Oliveira, R.G., 2021. Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1-2), pp.1-210. [PDF]
3. Yang, Q., Liu, Y., Chen, T. and Tong, Y., 2019. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10(2), pp.1-19. [PDF]
4. Li, T., Sahu, A.K., Talwalkar, A. and Smith, V., 2020. Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), pp.50-60. [PDF]
5. Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D. and Chandra, V., 2018. Federated learning with non-IID data. arXiv preprint arXiv:1806.00582. [PDF]
6. Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A. and Seth, K., 2017. Practical secure aggregation for privacy-preserving machine learning. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, pp.1175-1191. [PDF]
7. Wen, J., Zhang, Z., Lan, Y., Cui, Z., Cai, J. and Zhang, W., 2023. A survey on federated learning: Challenges and applications. International Journal of Machine Learning and Cybernetics, 14, pp.513-535. [PDF]