C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning

• URL: http://arxiv.org/abs/2411.00311v1
• Date: Fri, 01 Nov 2024 02:07:38 GMT
• Title: C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning
• Authors: Yeachan Kim, Junho Kim, Wing-Lam Mok, Jun-Hyung Park, SangKeun Lee,
• Abstract summary: We propose a novel hypernetwork-based FL framework that generates client-specific adapters by conditioning the client information. With the effectiveness of the hypernetworks in generating customized weights through learning, C2A can maximize the utility of shared model parameters. Comprehensive evaluation results clearly support the superiority of C2A in terms of both efficiency and effectiveness in FL scenarios.
• Score: 21.914696641277054
• License:
• Abstract: Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the training model has to be distributed between a server and clients. One potential solution to bypass such constraints might be the use of parameter-efficient fine-tuning (PEFT) in the context of FL. However, we have observed that typical PEFT tends to severely suffer from heterogeneity among clients in FL scenarios, resulting in unstable and slow convergence. In this paper, we propose Client-Customized Adaptation (C2A), a novel hypernetwork-based FL framework that generates client-specific adapters by conditioning the client information. With the effectiveness of the hypernetworks in generating customized weights through learning to adopt the different characteristics of inputs, C2A can maximize the utility of shared model parameters while minimizing the divergence caused by client heterogeneity. To verify the efficacy of C2A, we perform extensive evaluations on FL scenarios involving heterogeneity in label and language distributions. Comprehensive evaluation results clearly support the superiority of C2A in terms of both efficiency and effectiveness in FL scenarios.

Related papers

• Selective Knowledge Sharing for Personalized Federated Learning Under Capacity Heterogeneity [12.333226301343029]
  Pa3dFL is a novel framework designed to enhance local model performance by decoupling and selectively sharing knowledge among capacity-heterogeneous models. We conduct extensive experiments on three datasets to evaluate the effectiveness of Pa3dFL.
  arXiv  Detail & Related papers  (2024-05-31T02:59:25Z)
• Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
  Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training. In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework. Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
  arXiv  Detail & Related papers  (2023-08-11T09:58:47Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees [95.87604231887353]
  Existing pFL methods introduce high communication and computation costs or are vulnerable to test communication. In PerAda, a parameter distillation and pFL pFL has superior performance, especially under test-time distribution. Our code is available at https://github.com/NV/PerAda.
  arXiv  Detail & Related papers  (2023-02-13T19:00:37Z)
• Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning [28.185096784982544]
  Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. We propose a heterogeneous-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3$times$ speedup compared to other methods.
  arXiv  Detail & Related papers  (2022-12-19T14:19:07Z)
• Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [104.19414150171472]
  Attributes skews the current federated learning (FL) frameworks from consistent optimization directions among the clients. We propose disentangled federated learning (DFL) to disentangle the domain-specific and cross-invariant attributes into two complementary branches. Experiments verify that DFL facilitates FL with higher performance, better interpretability, and faster convergence rate, compared with SOTA FL methods.
  arXiv  Detail & Related papers  (2022-06-14T13:12:12Z)
• Combating Client Dropout in Federated Learning via Friend Model Substitution [8.325089307976654]
  Federated learning (FL) is a new distributed machine learning framework known for its benefits on data privacy and communication efficiency. This paper studies a passive partial client participation scenario that is much less well understood. We develop a new algorithm FL-FDMS that discovers friends of clients whose data distributions are similar. Experiments on MNIST and CIFAR-10 confirmed the superior performance of FL-FDMS in handling client dropout in FL.
  arXiv  Detail & Related papers  (2022-05-26T08:34:28Z)
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy [142.5983499872664]
  In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement.
  arXiv  Detail & Related papers  (2021-06-20T13:51:18Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.