↓Skip to main content

Federated Learning

Why Go Full? Elevating Federated Learning Through Partial Network Updates
·3064 words·15 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Beihang University
FedPart boosts federated learning by updating only parts of the network, solving the layer mismatch problem, and achieving faster convergence with higher accuracy.
Unravelling in Collaborative Learning
·214 words·2 mins· loading · loading
Machine Learning Federated Learning 🏢 École Polytechnique
Strategic data contributors with varying data quality can cause collaborative learning systems to ‘unravel’, but a novel probabilistic verification method effectively mitigates this, ensuring a stable…
Universal Sample Coding
·2065 words·10 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Imperial College London
Universal Sample Coding revolutionizes data transmission by reducing bits needed to communicate multiple samples from an unknown distribution, achieving significant improvements in federated learning …
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
·2932 words·14 mins· loading · loading
Machine Learning Federated Learning 🏢 UC San Diego
TAKFL, a novel federated learning framework, tackles device heterogeneity by independently distilling knowledge from diverse devices and integrating it adaptively, achieving state-of-the-art performan…
Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
·2669 words·13 mins· loading · loading
Machine Learning Federated Learning 🏢 Hong Kong University of Science and Technology
TIME-FFM: a Federated Foundation Model empowers time series forecasting using pre-trained Language Models, tackling data scarcity and privacy concerns for superior few-shot and zero-shot predictions.
The Power of Extrapolation in Federated Learning
·2710 words·13 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 GenAI Center of Excellence
Federated learning gets a speed boost: New extrapolation strategies significantly improve FedProx’s convergence, offering both theoretical backing and practical enhancements.
Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
·3467 words·17 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 University of Florida
FedPLVM tames cross-domain variance in federated prototype learning using dual-level clustering and an a-sparsity loss, achieving superior performance.
Stabilized Proximal-Point Methods for Federated Optimization
·1402 words·7 mins· loading · loading
Federated Learning 🏢 Saarland University
S-DANE & ACC-S-DANE achieve best-known communication complexity for federated learning, improving local computation efficiency via stabilized proximal-point methods.
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
·2907 words·14 mins· loading · loading
Machine Learning Federated Learning 🏢 ETH Zurich
SPEAR, a novel algorithm, precisely reconstructs entire data batches from gradients in federated learning, defying previous limitations and enhancing privacy risk assessment.
SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
·2099 words·10 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Virginia Tech
SpaFL: A communication-efficient federated learning framework that optimizes sparse model structures with low computational overhead by using trainable thresholds to prune model parameters.
SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
·362 words·2 mins· loading · loading
Machine Learning Federated Learning 🏢 Technion
SLowcal-SGD, a new local update method for distributed learning, provably outperforms Minibatch-SGD and Local-SGD in heterogeneous settings by using a slow querying technique, mitigating bias from loc…
Sketching for Distributed Deep Learning: A Sharper Analysis
·3663 words·18 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 University of Illinois Urbana-Champaign
This work presents a sharper analysis of sketching for distributed deep learning, eliminating the problematic dependence on ambient dimension in convergence analysis and proving ambient dimension-inde…
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
·2146 words·11 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 KAUST AIRI
Shadowheart SGD achieves optimal time complexity for asynchronous SGD in distributed settings with arbitrary computation and communication heterogeneity.
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
·1913 words·9 mins· loading · loading
Machine Learning Federated Learning 🏢 CMAP, UMR 7641, École Polytechnique
SCAFFLSA tames heterogeneity in federated learning, achieving logarithmic communication complexity and linear sample complexity.
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
·2189 words·11 mins· loading · loading
Machine Learning Federated Learning 🏢 National University of Singapore
RFLPA: Secure Federated Learning resists poisoning attacks via efficient secure aggregation.
Revisiting Ensembling in One-Shot Federated Learning
·3849 words·19 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 EPFL
FENS: a novel federated ensembling scheme that boosts one-shot federated learning accuracy to near iterative FL levels, while maintaining low communication costs.
Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
·2066 words·10 mins· loading · loading
Machine Learning Federated Learning 🏢 Princeton University
Probabilistic Federated Prompt Tuning (PFPT) significantly improves federated learning accuracy on heterogeneous and imbalanced data by using a probabilistic model for prompt aggregation, outperformin…
Private and Personalized Frequency Estimation in a Federated Setting
·1856 words·9 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Carnegie Mellon University
This paper introduces a novel privacy-preserving algorithm for personalized frequency estimation in federated settings, significantly improving accuracy and efficiency over existing methods.
pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning
·1986 words·10 mins· loading · loading
Machine Learning Federated Learning 🏢 Pennsylvania State University
pFedClub: Controllable heterogeneous model aggregation boosts personalized federated learning by generating reasonable-sized, personalized models, significantly cutting computational costs.
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
·1253 words·6 mins· loading · loading
Machine Learning Federated Learning 🏢 UC Irvine
Fed-POE: A personalized federated learning algorithm for superior real-time predictions!