FedTSV introduces Trajectory Shapley Value to dynamically weight client updates in federated learning based on their impact on the optimization trajectory for better fairness and stability.
hub Canonical reference
Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
Canonical reference. 100% of citing Pith papers cite this work as background.
33
Pith papers citing it
Background
100% of classified citations
abstract
Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We show that performance degrades as distributions differ more, and propose a mitigation strategy via server momentum. Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings.
hub tools
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
Federated martingale posterior sampling lets clients share data embeddings for central predictive Bayesian sampling, matching centralized performance and improving calibration on MNIST, CIFAR-10, and CIFAR-100.
Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.
FedGUI is the first comprehensive benchmark for federated GUI agents that studies cross-platform, cross-device, cross-OS, and cross-source heterogeneity, with experiments showing performance gains from cross-platform collaboration and identifying platform and OS as the most influential factors.
FedBCGD reduces communication in federated learning by a factor of 1/N through block-wise parameter updates with accelerated convergence guarantees.
DP-FedAdamW delivers an unbiased second-moment estimator for AdamW in DPFL, proving linear convergence acceleration without heterogeneity assumptions and outperforming SOTA by 5.83% on Tiny-ImageNet with Swin-Base at ε=1.
A single global merge at the final step of decentralized SGD matches the convergence rate of parallel SGD while improving test accuracy under high data heterogeneity.
Derives tractable optimal fair multi-class classifier and supplies in-processing and post-processing algorithms that converge to the accuracy-fairness Pareto frontier.
FedSmoothLoRA improves federated LoRA fine-tuning by constructing local initializations from a round-matching matrix for cross-round continuity and a gradient-aligned matrix for client-specific guidance, yielding faster convergence than prior methods in image and text tasks.
OmniISR unifies centralized, federated, and hybrid learning by injecting mutual-information supervision and negative-entropy regularization at multiple hidden layers, with supporting convergence and drift bounds.
UB-SMoE balances expert utilization in heterogeneous federated SMoE fine-tuning via Dynamic Modulated Routing and Universal Pseudo-Gradient, delivering up to 45% compute reduction and 8.7x performance gains for low-resource clients over prior LoRA-rank methods.
Rescaled ASGD recovers convergence to the true global objective by rescaling worker stepsizes proportional to computation times, matching the known time lower bound in the leading term under non-convex smoothness and bounded heterogeneity.
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.
PRISM maintains per-expert gradient subspace bases preserved under FedAvg to resolve spurious isolation in federated multimodal continual learning, outperforming 16 baselines with larger gains on longer task sequences.
RCSR is a personalization-friendly federated framework that improves cross-modal retrieval accuracy and stability under missing modalities via semantic routing and adapters.
SecureGate reduces PII leakage up to 31.66X in federated LLM fine-tuning via token-gated dual LoRA adapters while preserving utility and achieving perfect routing reliability.
DeepFedNAS delivers up to 1.21% higher accuracy and 61x faster architecture search for federated learning on heterogeneous IoT by replacing random supernet sampling with Pareto-optimal elite architectures and using a multi-objective fitness function as a zero-cost proxy.
DFedReweighting is a unified reweighting method for decentralized federated learning that customizes aggregation via target metrics and strategies to improve fairness, Byzantine robustness, and other objectives while proving linear convergence under standard assumptions.
Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.
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.
CRAFT derives a closed-form solution for conflict-resolved aggregation in federated learning via geometric constraints and projection, with theoretical support for common descent and empirical gains on heterogeneous data.
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
AFU-IC decouples client unlearning from global federated training in medical imaging and adds server-side invariance calibration to prevent relearning of erased data.
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
citing papers explorer
-
Fairness-Aware Federated Learning with Trajectory Shapley Value
FedTSV introduces Trajectory Shapley Value to dynamically weight client updates in federated learning based on their impact on the optimization trajectory for better fairness and stability.
-
Federated Martingale Posterior Samping
Federated martingale posterior sampling lets clients share data embeddings for central predictive Bayesian sampling, matching centralized performance and improving calibration on MNIST, CIFAR-10, and CIFAR-100.
-
When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity
Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.
-
FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems
FedGUI is the first comprehensive benchmark for federated GUI agents that studies cross-platform, cross-device, cross-OS, and cross-source heterogeneity, with experiments showing performance gains from cross-platform collaboration and identifying platform and OS as the most influential factors.
-
FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
FedBCGD reduces communication in federated learning by a factor of 1/N through block-wise parameter updates with accelerated convergence guarantees.
-
DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models
DP-FedAdamW delivers an unbiased second-moment estimator for AdamW in DPFL, proving linear convergence acceleration without heterogeneity assumptions and outperforming SOTA by 5.83% on Tiny-ImageNet with Swin-Base at ε=1.
-
On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning
A single global merge at the final step of decentralized SGD matches the convergence rate of parallel SGD while improving test accuracy under high data heterogeneity.
-
Demystifying the Optimal Fair Classifier in Multi-Class Classification
Derives tractable optimal fair multi-class classifier and supplies in-processing and post-processing algorithms that converge to the accuracy-fairness Pareto frontier.
-
FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
FedSmoothLoRA improves federated LoRA fine-tuning by constructing local initializations from a round-matching matrix for cross-round continuity and a gradient-aligned matrix for client-specific guidance, yielding faster convergence than prior methods in image and text tasks.
-
OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization
OmniISR unifies centralized, federated, and hybrid learning by injecting mutual-information supervision and negative-entropy regularization at multiple hidden layers, with supporting convergence and drift bounds.
-
UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models
UB-SMoE balances expert utilization in heterogeneous federated SMoE fine-tuning via Dynamic Modulated Routing and Universal Pseudo-Gradient, delivering up to 45% compute reduction and 8.7x performance gains for low-resource clients over prior LoRA-rank methods.
-
Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
Rescaled ASGD recovers convergence to the true global objective by rescaling worker stepsizes proportional to computation times, matching the known time lower bound in the leading term under non-convex smoothness and bounded heterogeneity.
-
FedVSSAM: Mitigating Flatness Incompatibility in Sharpness-Aware Federated Learning
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.
-
PRISM: Exposing and Resolving Spurious Isolation in Federated Multimodal Continual Learning
PRISM maintains per-expert gradient subspace bases preserved under FedAvg to resolve spurious isolation in federated multimodal continual learning, outperforming 16 baselines with larger gains on longer task sequences.
-
Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
RCSR is a personalization-friendly federated framework that improves cross-modal retrieval accuracy and stability under missing modalities via semantic routing and adapters.
-
SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs
SecureGate reduces PII leakage up to 31.66X in federated LLM fine-tuning via token-gated dual LoRA adapters while preserving utility and achieving perfect routing reliability.
-
DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training
DeepFedNAS delivers up to 1.21% higher accuracy and 61x faster architecture search for federated learning on heterogeneous IoT by replacing random supernet sampling with Pareto-optimal elite architectures and using a multi-objective fitness function as a zero-cost proxy.
-
DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning
DFedReweighting is a unified reweighting method for decentralized federated learning that customizes aggregation via target metrics and strategies to improve fairness, Byzantine robustness, and other objectives while proving linear convergence under standard assumptions.
-
Adaptive Federated Optimization
Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.
-
FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
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.
-
CRAFT: Conflict-Resolved Aggregation for Federated Training
CRAFT derives a closed-form solution for conflict-resolved aggregation in federated learning via geometric constraints and projection, with theoretical support for common descent and empirical gains on heterogeneous data.
-
FedSDR: Federated Self-Distillation with Rectification
FedSDR augments federated self-distillation with dual LoRA streams (local smoothing and global rectification) to produce globally aligned, factually faithful models under statistical heterogeneity.
-
Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging
AFU-IC decouples client unlearning from global federated training in medical imaging and adds server-side invariance calibration to prevent relearning of erased data.
-
PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.
-
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.
-
FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher
FedQUIT performs on-device unlearning in federated learning by distilling from a virtual teacher that penalizes true-class confidence on forget data while preserving other output relationships, matching or exceeding prior methods with lower overhead than retraining.
-
Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization
FedInit uses reverse personalized initialization in FL to reduce client drift effects, showing via excess risk that inconsistency impacts generalization error more than optimization error.
-
FedNSAM:Consistency of Local and Global Flatness for Federated Learning
FedNSAM uses global Nesterov momentum to make local flatness consistent with global flatness in federated learning, yielding tighter convergence than FedSAM and better empirical performance.
-
Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Data
Introduces M-DSL algorithm for distributed swarm learning that selects workers using a new non-i.i.d. degree metric to improve convergence and accuracy under data heterogeneity, with theoretical analysis and experiments on heterogeneous datasets.
-
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
DeTrigger detects and mitigates backdoor attacks in federated learning via gradient analysis and temperature scaling, claiming up to 251x faster detection and 98.9% attack reduction on four datasets with minimal accuracy loss.
-
A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
Federated aggregation strategies show distinct performance trade-offs in accuracy, loss, and efficiency depending on whether client data distributions are homogeneous or heterogeneous.
-
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
- Random Walk Learning and the Pac-Man Attack