Federated & Distributed Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Learning without centralizing data demands communication-efficient optimization. These papers establish FedAvg, heterogeneity, and adaptive federated methods.

Federated & Distributed Learning: 10 key papers

1. Communication-Efficient Learning of Deep Networks from Decentralized Data
   McMahan et al. arXiv 2016.
2. Federated Optimization in Heterogeneous Networks
   Li et al. arXiv 2018.
3. On the Convergence of FedAvg on Non-IID Data
   Li et al. arXiv 2019.
4. SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
   Karimireddy et al. arXiv 2019.
5. Advances and Open Problems in Federated Learning
   Kairouz et al. arXiv 2019.
6. Local SGD Converges Fast and Communicates Little
   Stich. arXiv 2018.
7. Adaptive Federated Optimization
   Reddi et al. arXiv 2020.
8. Federated Learning: Strategies for Improving Communication Efficiency
   Konečný et al. arXiv 2016.
9. Federated Learning with Matched Averaging
   Wang et al. arXiv 2020.
10. Federated Learning: Challenges, Methods, and Future Directions
    Li et al. arXiv 2019.

Related reading lists

• Communication in Multi-Agent RL
• Optimization for Deep Learning
• Active Learning & Adaptive Sampling
• Hyperparameter Optimization & AutoML
• Multi-Task & Transfer Reinforcement Learning
• Policy Gradient Methods
• Bayesian Optimization & Global Optimization
• Swarm RL & Collective Behavior