FedLog: Personalized Federated Classification with Less Communication and More Flexibility
Not on the map. Why?
Abstract (arXiv)
Federated representation learning (FRL) aims to learn personalized federated models with effective feature extraction from local data. FRL algorithms that share the majority of the model parameters face significant challenges with huge communication overhead. This overhead stems from the millions of neural network parameters and slow aggregation progress of the averaging heuristic. To reduce the overhead, we propose to share sufficient data summaries instead of raw model parameters. The data summaries encode minimal sufficient statistics of an exponential family, and Bayesian inference is utilized for global aggregation. It helps to reduce message sizes and communication frequency. To further ensure formal privacy guarantee, we extend it with differential privacy framework. Empirical results demonstrate high learning accuracy with low communication overhead of our method.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 11 Jul 2024.
Builds on
32 of 53 references.
References · 32
- 2017Attention Is All You Needcited by 59,932
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2018LEAF: A Benchmark for Federated Settingscited by 780
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
- 2019Federated Learning with Personalization Layerscited by 533
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2021Towards Personalized Federated Learningcited by 462
- 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
20 more
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
- 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
- 2013The Composition Theorem for Differential Privacycited by 290
- 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
- 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
- 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
- 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
- 2022Federated Learning with Partial Model Personalizationcited by 114
- 2020Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithmscited by 78
- 2020Federated Bayesian Optimization via Thompson Samplingcited by 77
- 2021Personalized Federated Learning with Gaussian Processescited by 76
- 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 75
- 2020Fast-Convergent Federated Learning with Adaptive Weightingcited by 67
- 2019Federated Learning with Bayesian Differential Privacycited by 60
- 2020Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applicationscited by 58
- 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
- 2023Eliminating Domain Bias for Federated Learning in Representation Spacecited by 38
- 2021QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learningcited by 26
- 2024Parametric Feature Transfer: One-shot Federated Learning with Foundation Modelscited by 13
- 2024Federated Representation Learning in the Under-Parameterized Regimecited by 7
Built on by
Not cited yet.