↓Skip to main content

Federated Learning

Personalized Federated Learning via Feature Distribution Adaptation
·2044 words·10 mins· loading · loading
Machine Learning Federated Learning 🏢 Northeastern University
Personalized federated learning (PFL) often struggles with data scarcity and distribution shifts. pFedFDA, a novel algorithm, tackles this by framing representation learning as a generative modeling …
Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
·7727 words·37 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 Hong Kong Polytechnic University
LM-WEATHER uses pre-trained language models to create highly accurate, personalized weather models directly on resource-constrained devices, achieving state-of-the-art results with significantly reduc…
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
·1504 words·8 mins· loading · loading
Machine Learning Federated Learning 🏢 Wuhan University
FDCR defends against backdoor attacks in heterogeneous federated learning by identifying malicious clients via Fisher Information-based parameter importance discrepancies and rescaling crucial paramet…
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
·1645 words·8 mins· loading · loading
Machine Learning Federated Learning 🏢 Stanford University
Researchers developed a verifiable training method that uses high-precision training with adaptive rounding and logging to achieve exact training replication across different GPUs, enabling efficient …
Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
·259 words·2 mins· loading · loading
Machine Learning Federated Learning 🏢 Wharton School of the University of Pennsylvania
This paper derives matching minimax bounds for distributed goodness-of-fit testing of discrete data under bandwidth or privacy constraints, bridging theory and practice in federated learning.
Optimal and Approximate Adaptive Stochastic Quantization
·2176 words·11 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 UCL
Researchers developed QUIVER, an efficient algorithm for adaptive stochastic quantization, solving a previously intractable problem in machine learning.
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
·2841 words·14 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 National University of Singapore
FedSD2C, a novel one-shot federated learning framework, tackles data heterogeneity and information loss by sharing synthetic distillates directly from local data, outperforming existing methods on com…
On the Necessity of Collaboration for Online Model Selection with Decentralized Data
·1427 words·7 mins· loading · loading
Machine Learning Federated Learning 🏢 School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen
Federated online model selection needs collaboration only when clients have limited computing power; otherwise, independent learning suffices.
On Sampling Strategies for Spectral Model Sharding
·1797 words·9 mins· loading · loading
Machine Learning Federated Learning 🏢 Qualcomm AI Research
Two novel sampling strategies for spectral model sharding in federated learning minimize approximation error and create unbiased estimators, improving performance on various datasets.
Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
·1738 words·9 mins· loading · loading
Machine Learning Federated Learning 🏢 KTH Royal Institute of Technology
This paper proposes a novel federated learning algorithm for nonconvex problems on compact smooth manifolds, achieving both computational and communication efficiency while mitigating client drift.
Low Precision Local Training is Enough for Federated Learning
·2011 words·10 mins· loading · loading
Machine Learning Federated Learning 🏢 Fudan University
Low-precision local training, surprisingly, is sufficient for accurate federated learning, significantly reducing communication and computation costs.
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
·3305 words·16 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 University of British Columbia
Local Superior Soups (LSS) significantly accelerates federated learning by efficiently merging pre-trained models, drastically cutting communication rounds without sacrificing accuracy.
Leveraging partial stragglers within gradient coding
·1641 words·8 mins· loading · loading
Machine Learning Federated Learning 🏢 Iowa State University
New gradient coding protocols efficiently leverage partial results from slow worker nodes, accelerating distributed training by approximately 2x and significantly improving accuracy.
Initializing Services in Interactive ML Systems for Diverse Users
·1498 words·8 mins· loading · loading
Machine Learning Federated Learning 🏢 University of Washington
Adaptively initializing multi-service ML systems for diverse users using minimal data, this paper introduces a randomized algorithm achieving near-optimal loss with provable guarantees.
Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
·1943 words·10 mins· loading · loading
Federated Learning 🏢 KAUST
MARINA-P and M3 algorithms drastically cut downlink and overall communication costs in nonconvex distributed optimization, scaling efficiently with the number of worker nodes.
HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links
·1515 words·8 mins· loading · loading
Machine Learning Federated Learning 🏢 Shanghai University of Electric Power
HyperPrism, a novel framework, tackles challenges in distributed machine learning by using adaptive non-linear aggregation to handle non-IID data and dynamic communication links, significantly improvi…
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
·2450 words·12 mins· loading · loading
AI Generated Machine Learning Federated Learning 🏢 University of Massachusetts, Amherst
HYDRA-FL: A novel hybrid knowledge distillation method makes federated learning robust against poisoning attacks while maintaining accuracy!
Hierarchical Federated Learning with Multi-Timescale Gradient Correction
·2189 words·11 mins· loading · loading
Machine Learning Federated Learning 🏢 Purdue University
MTGC tackles multi-timescale model drift in hierarchical federated learning.
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
·2418 words·12 mins· loading · loading
Machine Learning Federated Learning 🏢 University of Texas at Austin
HiCS-FL: A novel federated learning client sampling method that leverages data heterogeneity for faster, more efficient global model training in non-IID settings.
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
·2415 words·12 mins· loading · loading
Federated Learning 🏢 Hong Kong Baptist University
FuseFL achieves superior one-shot federated learning performance by leveraging a causal view of data heterogeneity and progressively fusing model blocks, significantly outperforming existing methods w…