An official website of the United States government
In this paper, we focus on the important yet understudied problem of Continual Federated Learning (CFL), where a server communicates with a set of clients to incrementally learn new concepts over time without sharing or storing any data. The complexity of this problem is compounded by challenges from both the Continual and Federated Learning perspectives. Specifically, models trained in a CFL setup suffer from catastrophic forgetting which is exacerbated by data heterogeneity across clients. Existing attempts at this problem tend to impose large overheads on clients and communication channels or require access to stored data which renders them unsuitable for real-world use due to privacy. We study this problem in the context of Foundation Models and showcase their effectiveness in mitigating forgetting while minimizing overhead costs and without requiring access to any stored data. We achieve this by leveraging a prompting based approach (such that only prompts and classifier heads have to be communicated) and proposing a novel and lightweight generation and distillation scheme to aggregate client models at the server. We formulate this problem for image classification and establish strong baselines for comparison, conduct experiments on CIFAR-100 as well as challenging, large-scale datasets like ImageNet-R and DomainNet. Our approach outperforms both existing methods and our own baselines by more than 7% while significantly reducing communication and client-level computation costs.
more »
« less
This content will become publicly available on May 8, 2026
Quantifying Individual Fairness in Continual Federated Learning
Continual Federated Learning (CFL) is a distributed machine learning technique that enables multiple clients to collaboratively train a shared model without sharing their data, while also adapting to new classes without forgetting previously learned ones. This dynamic, adaptive learning process parallels the concept of founda- tion models in FL, where large, pre-trained models are fine-tuned in a decentralized, federated setting. While foundation models in FL leverage pre-trained knowledge as a starting point, CFL continu- ously updates the shared model as new tasks and data distributions emerge, requiring ongoing adaptation. Currently, there are limited evaluation models and metrics in measuring fairness in CFL, and ensuring fairness over time can be challenging as the system evolves. To address this challenge, this article explores temporal fairness in CFL, examining how the fairness of the model can be influenced by the selection and participation of clients over time. Based on individual fairness, we introduce a novel fairness metric that captures temporal aspects of client behavior and evaluates different client selection strategies for their impact on promoting fairness.
more »
« less
- Award ID(s):
- 2304213
- PAR ID:
- 10597749
- Publisher / Repository:
- ACM
- Date Published:
- ISBN:
- 9798400713316
- Page Range / eLocation ID:
- 1735 to 1743
- Format(s):
- Medium: X
- Location:
- Sydney NSW Australia
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Federated Learning (FL) enables edge devices or clients to collaboratively train machine learning (ML) models without sharing their private data. Much of the existing work in FL focuses on efficiently learning a model for a single task. In this paper, we study simultaneous training of multiple FL models using a common set of clients. The few existing simultaneous training methods employ synchronous aggregation of client updates, which can cause significant delays because large models and/or slow clients can bottleneck the aggregation. On the other hand, a naive asynchronous aggregation is adversely affected by stale client updates. We propose FedAST, a buffered asynchronous federated simultaneous training algorithm that overcomes bottlenecks from slow models and adaptively allocates client resources across heterogeneous tasks. We provide theoretical convergence guarantees of FedAST for smooth non-convex objective functions. Extensive experiments over multiple real-world datasets demonstrate that our proposed method outperforms existing simultaneous FL approaches, achieving up to 46.0% reduction in time to train multiple tasks to completion.more » « less
-
Federated learning is an emerging machine learning framework where models are trained using heterogeneous datasets collected by a large number of edge clients. Standard methods to aggregate local training models weigh each model by a fraction of data size at that client. However, such approaches result in unfairness to clients with small and unique datasets, leading to inferior accuracy of the global model at these clients. In this work, we propose a novel optimization framework called DRFL that dynamically adjusts the weight assigned to each client, and we combine it with a biased client selection strategy, both of which encourage fairness in federated training. We validate the effectiveness of our proposed method on a suite of both synthetic and real federated datasets, revealing the proposed method outperforms existing baselines in terms of resulting fairness.more » « less
-
In this paper, we focus on the important yet understudied problem of Continual Federated Learning (CFL), where a server communicates with a set of clients to incrementally learn new concepts over time without sharing or storing any data. The complexity of this problem is compounded by challenges from both the Continual and Federated Learning perspectives. Specifically, models trained in a CFL setup suffer from catastrophic forgetting which is exacerbated by data heterogeneity across clients. Existing attempts at this problem tend to impose large overheads on clients and communication channels or require access to stored data which renders them unsuitable for real-world use due to privacy. In this paper, we attempt to tackle forgetting and heterogeneity while minimizing overhead costs and without requiring access to any stored data. We study this problem in the context of Vision Transformers and explore parameter-efficient approaches to adapt to dynamic distributions while minimizing forgetting. We achieve this by leveraging a prompting based approach (such that only prompts and classifier heads have to be communicated) and proposing a novel and lightweight generation and distillation scheme to consolidate client models at the server. We formulate this problem for image classification and establish strong baselines for comparison, conduct experiments on CIFAR-100 as well as challenging, large-scale datasets like ImageNet-R and DomainNet. Our approach outperforms both existing methods and our own baselines by as much as 7% while significantly reducing communication and client-level computation costs. Code available at https://github.com/shaunak27/hepco-fed.more » « less
-
Bellet, Aurelien (Ed.)Federated learning (FL) aims to collaboratively train a global model using local data from a network of clients. To warrant collaborative training, each federated client may expect the resulting global model to satisfy some individual requirement, such as achieving a certain loss threshold on their local data. However, in real FL scenarios, the global model may not satisfy the requirements of all clients in the network due to the data heterogeneity across clients. In this work, we explore the problem of global model appeal in FL, which we define as the total number of clients that find that the global model satisfies their individual requirements. We discover that global models trained using traditional FL approaches can result in a significant number of clients unsatisfied with the model based on their local requirements. As a consequence, we show that global model appeal can directly impact how clients participate in training and how the model performs on new clients at inference time. Our work proposes MaxFL, which maximizes the number of clients that find the global model appealing. MaxFL achieves a 22-40% and 18-50% improvement in the test accuracy of training clients and (unseen) test clients respectively, compared to a wide range of FL approaches that tackle data heterogeneity, aim to incentivize clients, and learn personalized/fair models.more » « less
