LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
hub Canonical reference
Federated Learning with Non-IID Data
Canonical reference. 75% of citing Pith papers cite this work as background.
33
Pith papers citing it
Background
75% of classified citations
abstract
Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model for prediction, while keeping the training data local. This decentralized approach to train models provides privacy, security, regulatory and economic benefits. In this work, we focus on the statistical challenge of federated learning when local data is non-IID. We first show that the accuracy of federated learning reduces significantly, by up to 55% for neural networks trained for highly skewed non-IID data, where each client device trains only on a single class of data. We further show that this accuracy reduction can be explained by the weight divergence, which can be quantified by the earth mover's distance (EMD) between the distribution over classes on each device and the population distribution. As a solution, we propose a strategy to improve training on non-IID data by creating a small subset of data which is globally shared between all the edge devices. Experiments show that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.
hub tools
citation-role summary
background 7
other 1
citation-polarity summary
verdicts
UNVERDICTED 33representative citing papers
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
Unified convergence rates and tight lower bounds for Byzantine-robust distributed SGD under stochasticity and general data heterogeneity, showing local momentum reduces stochastic error floors.
A device-partitioning bandwidth allocation policy for federated learning over IIoT networks that provably reduces total training time compared to any non-partitioning scheme.
A single adversary in distributed training inflates its attribution value via latent optimization on synthetic batches without degrading accuracy or triggering basic defenses.
FedVSSAM mitigates flatness incompatibility in SAM-based federated learning by consistently using a variance-suppressed adjusted direction for local perturbation, descent, and global updates, with non-convex convergence guarantees.
ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.
AW-PSP dynamically weights node sampling by real-time availability predictions and failure correlations to improve robustness, label coverage, and fairness in federated learning under correlated device failures.
HierFedCEA delivers a hierarchical federated learning framework for privacy-preserving climate control optimization across heterogeneous CEA facilities, reaching 94% of centralized performance with under 1 MB communication.
Conditioning a global FL model on local PCA statistics of client data matches oracle cluster performance across heterogeneous settings and is robust to sparse data with zero added communication.
Hybrid QFL cuts quantum transmissions from 3TNMP to {3t + 2(T-t)}NMP over T rounds while preserving near-centralized convergence and improving depolarizing-noise resilience via decentralized aggregation and Steane-code QEC.
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
Fed-TaLoRA uses task-agnostic low-rank residual adaptation with post-aggregation calibration to enable efficient federated continual fine-tuning across sequential tasks under non-IID conditions.
SP-CACW is a convergence-aware client weighting scheme for selfish personalized federated learning that minimizes an upper bound on the target client's convergence error and can zero out harmful peers.
FedMPT applies causal modeling and LLM-driven condition prompts with optimal transport and gating to perform federated multi-label prompt tuning of VLMs, claiming competitive results on benchmarks.
FIRMA introduces Fibonacci ring aggregation protocols for server-free federated learning that maintain private heads and achieve higher accuracy than FedAvg under label skew across multiple benchmarks and heterogeneity regimes.
Proactive client selection in federated learning via differentially private mutual information and simulated annealing to optimize Potential Federation Loss for utility and fairness.
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
FedSurrogate defends federated learning against backdoors by clustering on security-critical layers and substituting malicious updates with benign surrogates, reporting false-positive rates below 10% and attack success below 2.1% under non-IID conditions.
Rennala MVR improves time complexity over Rennala SGD for smooth nonconvex stochastic optimization in heterogeneous parallel systems under a mean-squared smoothness assumption.
CLAD is a clustered federated learning framework with a dual-mode architecture for joint anomaly detection and attack classification in IoT using labeled and unlabeled data.
HeroCrystal achieves 33.4% mAP on cross-domain multi-camera object detection by combining one-shot diffusion-based synthetic data generation, probabilistic federated Faster R-CNN, and inconsistent-category distillation, outperforming prior privacy-preserving baselines by 2.1%.
FMCL performs one-shot class-aware client clustering in heterogeneous federated learning by deriving semantic signatures from foundation model embeddings and using cosine distance, yielding improved performance and stable clusters compared to prior methods.
REVERB-FL uses a server-side reserve set with retraining and adversarial training to reduce poisoning effects and speed convergence in federated audio classification under non-IID data.
citing papers explorer
-
REVERB-FL: Server-Side Adversarial and Reserve-Enhanced Federated Learning for Robust Audio Classification
REVERB-FL uses a server-side reserve set with retraining and adversarial training to reduce poisoning effects and speed convergence in federated audio classification under non-IID data.