arXiv research

Optimal client sampling reduces communication in federated learning.

A new FL algorithm reduces communication overhead by selectively updating model parameters.

FedLoRU improves FL efficiency by using low-rank updates.

Federated learning can be vulnerable to adversarial attacks, which this work addresses.

Study on incentivizing truthfulness in federated learning with heterogeneous data.

New framework detects and removes malicious model updates in federated learning.

FedShuffle improves local updates in FL, especially with data imbalance.

FedGLOMO accelerates FL convergence for non-convex functions.

FedAMD framework improves federated learning with partial client participation.

This paper evaluates and compares gradient leakage attacks in federated learning.

Synthetic data replaces model updates in federated learning.

FedElasticNet reduces communication costs and handles client drift in FL.

Bayesian method improves Federated Learning robustness against corrupted updates.

A framework for federated adversarial learning with convergence analysis.

New framework provides privacy guarantees for practical federated learning.

Collaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as gradients to the server. While data do not leave a client device, the communicated gra…

The increasing interest in user privacy is leading to new privacy preserving machine learning paradigms. In the Federated Learning paradigm, a master machine learning model is distributed to user clients, the clients use their locally stored data and model for both inference and calculating model updates. The model upd…

Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.

A framework for certified unlearning in decentralized federated learning.

Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol. However, this process assumes a trusted centralized infrastructure for coordination, and clients must…

Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates. In federated learning, bandwidth and privacy are two main concerns of gradient updates transmission. This paper proposes an end-to-end encrypted neural network for gradient updates transmiss…

Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of the clients. One challenge in federated learning is to reduce the client-server c…

Mime algorithm improves federated learning by adapting centralized methods.

Study finds non-IID data causes FL performance issues.

DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.

A federated minimax framework for heterogeneous clients.

Optimizes communication in federated learning using rate-distortion theory.

DoCoFL compresses model updates for cross-device federated learning.

NAC-FL optimizes model updates in FL systems by adapting compression to network congestion.

Unified analysis of FL with arbitrary client participation.

Federated learning algorithm improves with intermittent client availability.

Byzantine-resilient federated learning with local iterations and robust mean estimation.

FetchSGD reduces communication in federated learning with sketching.

Federated learning is a recently proposed paradigm that enables multiple clients to collaboratively train a joint model. It allows clients to train models locally, and leverages the parameter server to generate a global model by aggregating the locally submitted gradient updates at each round. Although the incentive mo…

This work addresses a new problem that learns generative adversarial networks (GANs) from multiple data collections that are each i) owned separately by different clients and ii) drawn from a non-identical distribution that comprises different classes. Given such non-iid data as input, we aim to learn a distribution in…

This work enables privacy-preserving model learning from single samples per client.

DPMM-CFL clusters clients for federated learning without fixed K, improving performance.

This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients with…

Federated Averaging (FedAvg) has emerged as the algorithm of choice for federated learning due to its simplicity and low communication cost. However, in spite of recent research efforts, its performance is not fully understood. We obtain tight convergence rates for FedAvg and prove that it suffers from `client-drift' w…

Asynchronous distributed stochastic gradient descent methods have trouble converging because of stale gradients. A gradient update sent to a parameter server by a client is stale if the parameters used to calculate that gradient have since been updated on the server. Approaches have been proposed to circumvent this pro…

This paper tackles objective inconsistency in federated optimization with heterogeneous clients.

FedSGM tackles constrained federated learning with unified framework.

FedNNNN improves FL by adjusting model update vector norms.

Locally adaptive federated learning improves convergence in distributed machine learning.

Study protects federated learning models from eavesdropping attacks.

MpFL models clients as strategic players to reach equilibrium with less communication.

New methods handle both data and network heterogeneity in federated learning.

Coded Federated Learning speeds up model convergence by preemptively computing on parity data.