REVIEW 6 cited by
LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Federated learning is a popular distributed machine learning paradigm with enhanced privacy. Its primary goal is learning a global model that offers good performance for the participants as many as possible. The technology is rapidly advancing with many unsolved challenges, among which statistical heterogeneity (i.e., non-IID) and communication efficiency are two critical ones that hinder the development of federated learning. In this work, we propose LotteryFL -- a personalized and communication-efficient federated learning framework via exploiting the Lottery Ticket hypothesis. In LotteryFL, each client learns a lottery ticket network (i.e., a subnetwork of the base model) by applying the Lottery Ticket hypothesis, and only these lottery networks will be communicated between the server and clients. Rather than learning a shared global model in classic federated learning, each client learns a personalized model via LotteryFL; the communication cost can be significantly reduced due to the compact size of lottery networks. To support the training and evaluation of our framework, we construct non-IID datasets based on MNIST, CIFAR-10 and EMNIST by taking feature distribution skew, label distribution skew and quantity skew into consideration. Experiments on these non-IID datasets demonstrate that LotteryFL significantly outperforms existing solutions in terms of personalization and communication cost.
Forward citations
Cited by 6 Pith papers
-
Sheaf-Based Federated Representation Learning
Sheaf-FRL learns per-edge orthogonal or Stiefel maps to align heterogeneous agent latent spaces through a sheaf-Laplacian gluing penalty evaluated on shared pilots, with decentralized convergence guarantees.
-
Sketched Gaussian Mechanism for Private Federated Learning
A sketched Gaussian mechanism is shown to have privacy loss that shrinks as the sketch dimension grows, giving communication-efficient federated learning with stronger privacy per noise budget.
-
Non-IID data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions
A comprehensive survey that organizes non-IID data in federated learning into taxonomies of skew types, partition protocols, and metrics, with a meta-analysis of 235 selected papers.
-
Decentralized Pliable Index Coding For Federated Learning In Intelligent Transportation Systems
Pliable index coding with consecutive side-information is used to shuffle synthetic data among federated learning nodes, reducing transmissions and improving convergence in ITS simulations.
-
A New Perspective on Privacy Protection in Federated Learning with Granular-Ball Computing
Granular-ball image compression into graphs improves privacy and efficiency in federated learning, but the paper does not show the claimed accuracy is maintained.
-
Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift
FEDMPR, combining magnitude pruning, dropout, and noise injection in local training, reports accuracy gains over standard federated baselines on several image benchmarks, though not consistently in all settings.
Discussion (0). Continue with ORCID to comment.