Mode Connectivity and Data Heterogeneity of Federated Learning

• URL: http://arxiv.org/abs/2309.16923v1
• Date: Fri, 29 Sep 2023 01:49:03 GMT
• Title: Mode Connectivity and Data Heterogeneity of Federated Learning
• Authors: Tailin Zhou, Jun Zhang, Danny H.K. Tsang
• Abstract summary: Federated learning (FL) enables multiple clients to train a model while keeping their data private collaboratively. Previous studies have shown that data heterogeneity between clients leads to drifts across client updates. We perform empirical and theoretical studies on the relationship between client and global modes.
• Score: 8.677832361022809
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning (FL) enables multiple clients to train a model while keeping their data private collaboratively. Previous studies have shown that data heterogeneity between clients leads to drifts across client updates. However, there are few studies on the relationship between client and global modes, making it unclear where these updates end up drifting. We perform empirical and theoretical studies on this relationship by utilizing mode connectivity, which measures performance change (i.e., connectivity) along parametric paths between different modes. Empirically, reducing data heterogeneity makes the connectivity on different paths more similar, forming more low-error overlaps between client and global modes. We also find that a barrier to connectivity occurs when linearly connecting two global modes, while it disappears with considering non-linear mode connectivity. Theoretically, we establish a quantitative bound on the global-mode connectivity using mean-field theory or dropout stability. The bound demonstrates that the connectivity improves when reducing data heterogeneity and widening trained models. Numerical results further corroborate our analytical findings.

Related papers

• Accelerated Stochastic ExtraGradient: Mixing Hessian and Gradient Similarity to Reduce Communication in Distributed and Federated Learning [50.382793324572845]
  Distributed computing involves communication between devices, which requires solving two key problems: efficiency and privacy. In this paper, we analyze a new method that incorporates the ideas of using data similarity and clients sampling. To address privacy concerns, we apply the technique of additional noise and analyze its impact on the convergence of the proposed method.
  arXiv  Detail & Related papers  (2024-09-22T00:49:10Z)
• Learning Divergence Fields for Shift-Robust Graph Representations [73.11818515795761]
  In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging problem with interdependent data. We derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains.
  arXiv  Detail & Related papers  (2024-06-07T14:29:21Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• Improving Group Connectivity for Generalization of Federated Deep Learning [8.594665698279522]
  Federated learning (FL) involves multiple clients collaboratively training a global model via iterative local updates and model fusion. In this paper, we study and improve FL's generalization through a fundamental connectivity'' perspective. We propose FedGuCci and FedGuCci+, improving group connectivity for better generalization.
  arXiv  Detail & Related papers  (2024-02-29T08:27:01Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [54.80435317208111]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm. It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities. It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)
• Heterogeneous Federated Learning via Personalized Generative Networks [7.629157720712401]
  Federated Learning (FL) allows several clients to construct a common global machine-learning model without having to share their data. We propose a method for knowledge transfer between clients where the server trains client-specific generators.
  arXiv  Detail & Related papers  (2023-08-25T09:37:02Z)
• DYNAFED: Tackling Client Data Heterogeneity with Global Dynamics [60.60173139258481]
  Local training on non-iid distributed data results in deflected local optimum. A natural solution is to gather all client data onto the server, such that the server has a global view of the entire data distribution. In this paper, we put forth an idea to collect and leverage global knowledge on the server without hindering data privacy.
  arXiv  Detail & Related papers  (2022-11-20T06:13:06Z)
• Realistic Counterfactual Explanations by Learned Relations [0.0]
  We propose a novel approach to realistic counterfactual explanations that preserve relationships between data attributes. The model directly learns the relationships by a variational auto-encoder without domain knowledge and then learns to disturb the latent space accordingly.
  arXiv  Detail & Related papers  (2022-02-15T12:33:51Z)
• FedRAD: Federated Robust Adaptive Distillation [7.775374800382709]
  Collaborative learning framework by typically aggregating model updates is vulnerable to model poisoning attacks from adversarial clients. We propose a novel robust aggregation method, Federated Robust Adaptive Distillation (FedRAD), to detect adversaries and robustly aggregate local models. The results show that FedRAD outperforms all other aggregators in the presence of adversaries, as well as in heterogeneous data distributions.
  arXiv  Detail & Related papers  (2021-12-02T16:50:57Z)
• Layer-wise Adaptive Model Aggregation for Scalable Federated Learning [11.669431684184536]
  In Federated Learning, a common approach for aggregating local models across clients is periodic averaging of the full model parameters. We propose FedLAMA, a layer-wise model aggregation scheme for scalable Federated Learning.
  arXiv  Detail & Related papers  (2021-10-19T22:49:04Z)
• FedKD: Communication Efficient Federated Learning via Knowledge Distillation [56.886414139084216]
  Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. We propose a communication efficient federated learning method based on knowledge distillation.
  arXiv  Detail & Related papers  (2021-08-30T15:39:54Z)

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.