DeepAI AI Chat
Log In Sign Up

Personalized Federated Learning using Hypernetworks

by   Aviv Shamsian, et al.

Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, while maintaining the capacity to generate unique and diverse personal models. Furthermore, since hypernetwork parameters are never transmitted, this approach decouples the communication cost from the trainable model size. We test pFedHN empirically in several personalized federated learning challenges and find that it outperforms previous methods. Finally, since hypernetworks share information across clients we show that pFedHN can generalize better to new clients whose distributions differ from any client observed during training.


An Empirical Study of Personalized Federated Learning

Federated learning is a distributed machine learning approach in which a...

Find Your Friends: Personalized Federated Learning with the Right Collaborators

In the traditional federated learning setting, a central server coordina...

Visual Prompt Based Personalized Federated Learning

As a popular paradigm of distributed learning, personalized federated le...

On Bridging Generic and Personalized Federated Learning

Federated learning is promising for its ability to collaboratively train...

Federated Learning of Shareable Bases for Personalization-Friendly Image Classification

Personalized federated learning (PFL) aims to harness the collective wis...

Personalized Federated Learning with Gaussian Processes

Federated learning aims to learn a global model that performs well on cl...

Comfetch: Federated Learning of Large Networks on Memory-Constrained Clients via Sketching

A popular application of federated learning is using many clients to tra...