Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

By Alireza Fallah, Aryan Mokhtari, Asuman E. Ozdaglar. 2020

1,273 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Mang Ye
2. Mingzhe Chen
3. Khaled Ben Letaief
4. Dacheng Tao
5. Bo Du
6. Yuanming Shi
7. Walid Saad
8. Medhi Bennis

Citations in the corpus

• Robust Aggregation for Federated Learning (2019, background): “Extensions were proposed in [7, 29, 33, 47, 50, 57, 69, 75, 79]; see also the recent surveys [46, 56].”
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications (2021, background): “…various effective and personalized models have been proposed to rectify the original model (1), including regularizing local loss functions at each device [134], [135], [136], distributionally robust modeling [137], [138], multi-task learning [139], as well as the meta-learning approaches [140].”
• Distributed Learning in Wireless Networks: Recent Progress and Future Challenges (2021, background): “FL algorithms: federated multi-task learning [35] and model agnostic meta learning (MAML) based FL [36].”
• Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, methodology): “, sharing partial structures [35, 139], model optimization [46, 118, 124], knowledge transfer [48, 85].”
• FedScale: Benchmarking Model and System Performance of Federated Learning at Scale (2021, background): “Instead of training a single global model, some efforts train a mixture of models (Shi et al., 2021; Fallah et al., 2020), cluster clients over training (Ghosh et al.”
• FedProto: Federated Prototype Learning across Heterogeneous Clients (2021, background): “(Fallah, Mokhtari, and Ozdaglar 2020) applies meta-training strategy for personalized FL. Heterogeneous model architecture is another major challenging scenario of FL.”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “…the final model against external attackers and (2) using the splitting techniques described in Section 2.3.3 to personalize the model for each participant by splitting the global model, for instance, allowing the participants to privately hold some special layers for their individual goals [48].”
• FedScale: Benchmarking Model and System Performance of Federated Learning (2021, background): “Instead of training a single global model, some efforts resort to training a mixture of models [10, 12], clustering clients over training [16], or enforcing guided client selection [24]; To tackle the scarce and heterogeneous device resource, FedAvg [29] reduces communication cost by performing mult”
• Data-Free Knowledge Distillation for Heterogeneous Federated Learning (2021, methodology): “…a wealth of work has been proposed to handle user heterogeneity, by regularizing model weight updates (Li et al., 2020b), allowing personalized user models (Fallah et al., 2020; Dinh et al., 2020), or introducing new model aggregation schemes (Yurochkin et al., 2019; Mansour et al., 2020).”
• FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout (2021, background): “, 2020a) among clients (Smith et al., 2017; Li & Wang, 2019; Hsieh et al., 2020; Fallah et al., 2020; Li et al., 2020c), the system heterogeneity has largely remained unaddressed.”
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, methodology): “Per-FedAvg [52] applies the idea of model-agnostic meta-learning [55] framework in FedAvg.”
• FedALA: Adaptive Local Aggregation for Personalized Federated Learning (2022, methodology): “Recent pFL studies on model aggregation on the server can be classified into three categories: (1) methods that learn a single global model and fine-tune it, including Per-FedAvg (Fallah, Mokhtari, and Ozdaglar 2020) and FedRep (Collins et al. 2021), (2) methods that learn additional personalized mo”