REVIEW 21 cited by
Federated Learning Based on Dynamic Regularization
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
read the original abstract
We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round. We view Federated Learning problem primarily from a communication perspective and allow more device level computations to save transmission costs. We point out a fundamental dilemma, in that the minima of the local-device level empirical loss are inconsistent with those of the global empirical loss. Different from recent prior works, that either attempt inexact minimization or utilize devices for parallelizing gradient computation, we propose a dynamic regularizer for each device at each round, so that in the limit the global and device solutions are aligned. We demonstrate both through empirical results on real and synthetic data as well as analytical results that our scheme leads to efficient training, in both convex and non-convex settings, while being fully agnostic to device heterogeneity and robust to large number of devices, partial participation and unbalanced data.
Forward citations
Cited by 21 Pith papers
-
FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity
Global-aware coordinate trust modulation after corrected AdamW updates improves federated Transformer and LLM training under data heterogeneity over strong adaptive baselines.
-
AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning
AS-FedBridge trains a shared pseudo-spike bridge so ANN and SNN clients in federated learning can align representations and improve collaborative accuracy.
-
TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement
TriShield combines artifact detection, Adam momentum pre-entanglement, and SVD task-subspace projection to drive NeuroImprint reconstruction to 0% with claimed near-zero utility loss.
-
FM$^2$: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging
FM² uses dual mixture-of-experts (per-class local, per-modality shared) with a proximal alignment regularizer to train federated medical imaging models across overlapped and disjoint modality settings, reporting consi...
-
Degree of Staleness-Aware Data Updating in Federated Learning
DUFL is a payment-based incentive mechanism that jointly balances data staleness and data volume via a Stackelberg game and derives a closed-form optimal client data update strategy.
-
FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios
FedWCM uses per-client data-distribution scores to adapt momentum and aggregation weights in federated learning, showing empirical gains over FedAvg and FedCM on long-tailed non-IID datasets, but its convergence proof...
-
AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning
AFBS scores buffered gradients by staleness and dataset size, discards low-value ones, and clusters clients through random-projection-encrypted label distributions before aggregation in semi-asynchronous federated learning.
-
Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
Sparse zeroth-order federated fine-tuning with shared seeds and GradIP-based early stopping matches or beats full-parameter ZO while using far less communication.
-
Label-shift robust federated feature screening for high-dimensional classification
A new label-shift robust utility, LR-FFS, is proposed for federated feature screening, with a unifying framework, distributed estimation, and FDR control.
-
HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning
HERO shows that FCL method rankings shift when client data skew and task-order mismatch are controlled separately, and that average accuracy can hide weak bottom-client performance.
-
One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification
Per-class closed-form ridge aggregation reproduces the centralized balanced-label classifier in one round and outperforms gradient-based federated baselines on ChestXray14 under missing-class heterogeneity.
-
Adaptive Federated Learning to Optimize Integrated Flows in Cyber-Physical Data Centers
An adaptive federated learning-to-optimization method with a rejection-capable acceptance rule and verifiable double aggregation achieves near-centralized cost for data center energy management without exposing local data.
-
Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis
A top-rho gradient masking plus influence-weighted averaging method (FedIA) improves federated graph learning accuracy and stability under domain shift.
-
Multi-Hop Privacy Propagation for Differentially Private Federated Learning in Social Networks
A game-theoretic mechanism for differentially private federated learning that accounts for multi-hop privacy leakage over social networks, claimed to achieve near-optimal social welfare with lower server cost.
-
Distilling A Universal Expert from Clustered Federated Learning
A federated learning method that distills a universal model from cluster-specific models using data-free knowledge distillation and adaptive label weighting.
-
Towards Graph-Based Privacy-Preserving Federated Learning: ModelNet -- A ResNet-based Model Classification Dataset
ModelNet creates three CIFAR-100-based benchmarks with controlled semantic diversity across 5,000 client subsets.
-
Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data
FedProj combines client-side gradient projection onto a global-knowledge loss with server-side ensemble distillation and outperforms existing federated learning methods on non-IID image and NLP benchmarks.
-
Distributionally Robust Federated Learning with Client Drift Minimization
DRDM combines DRO and FedDyn-style dynamic regularization to improve worst-case client accuracy in federated learning, with a claimed O(1/T^{3/8}) duality-gap convergence rate.
-
FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
A quadruplet-based loss for federated learning that aims to reduce representational collapse under data heterogeneity, with mixed empirical support.
-
Generalizable Federated Learning using Client Adaptive Focal Modulation
The abstract describes AdaptFED, a claimed federated learning method, but the full text is an unrelated graph theory paper, so the claimed results are absent from the submission.
-
UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data
UniVarFL adds a classifier variance regularizer and a hyperspherical uniformity regularizer to local federated training, reporting improved accuracy on some non-IID benchmarks but not consistently across its own experiments.
Discussion (0). Sign in to comment.