arXiv research

This paper analyzes and improves convergence in federated learning with biased client selection.

We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning. We show useful settings under which each method outperforms the other in terms of communication efficiency. We consider various practical scenarios of distributed learning setup and …

Federated learning improves by training central model with client model outputs.

Federated Learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a centralized server. This form of privacy-preserving collaborative learning however comes at the cost of a significant communication overhead du…

pFedGP uses Gaussian processes for personalized federated learning with improved kernel learning.

Federated learning supports exact support recovery with minimal communication.

This paper develops a federated approach to learn Granger causality in interdependent industrial clients.

Boosting-inspired framework for federated learning with progressive model personalization.

Decentralized learning achieves centralized performance via Gibbs measures.

SPIRE enables efficient federated learning for diffusion models by separating client-specific embeddings from a shared backbone.

Optimal privacy and accuracy in distributed mean estimation with compression.

Clust-PSI-PFL uses PSI to improve accuracy and fairness in federated learning.

New bounds on learning shared representations improve model performance and efficiency.

FedDuA adapts global learning rate for federated learning.

Paper analyzes Scaffold algorithm for federated learning, proving linear speed-up with stochastic gradients.

Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers…

Client adaptation improves federated learning performance with non-IID data.

Paper proposes a fair stock trading strategy using multi-agent reinforcement learning.

FedSTaS stratifies and samples clients for efficient FL.

Federated MTL learns personalized models under mixed distributions.

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

This paper optimizes brokerage contracts for multiple clients trading a single asset.

We certify federated learning model performance under meta-distribution shifts.

Personalized federated learning for diverse client objectives.

With the wealth of information produced by social networks, smartphones, medical or financial applications, speculations have been raised about the sensitivity of such data in terms of users' personal privacy and data security. To address the above issues, Federated Learning (FL) has been recently proposed as a means t…

This paper improves bond market making by adjusting hit-ratios for client flow quality.

A new scheme for private computation splits client data into shares for server operations.

This work detects anomalous clients in federated learning to prevent their adverse impacts.

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to s…

A federated minimax framework for heterogeneous clients.

FedAMD framework improves federated learning with partial client participation.

Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients. Downloading models and uploading gradients uses the client's bandwidth, so minimizing these transmission costs is…

Robo-advisor improves investment advice through client interaction.

Federated framework learns causal states to predict counterfactuals without centralizing data.

Unified Bayesian framework for clustered federated learning improves model performance.

A novel hierarchical Bayesian approach to Federated Learning reduces data exposure and improves convergence rates.

FLowDUP trains personalized models with unlabeled clients in low dimensions.

Federated learning algorithm improves with intermittent client availability.

The recent surge of text-based online counseling applications enables us to collect and analyze interactions between counselors and clients. A dataset of those interactions can be used to learn to automatically classify the client utterances into categories that help counselors in diagnosing client status and predictin…

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

Group personalization improves FL performance in heterogeneous client data.

Study evaluates federated learning for ICU survival prediction using eICU data.

FedACS uses attention to select clients with similar data for federated learning.

Unified analysis of FL with arbitrary client participation.

This paper analyzes deep federated learning for low-dimensional data, revealing intrinsic dimensionality's role in convergence rates.

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…

Optimal client sampling reduces communication in federated learning.

New method for decentralized learning from diverse clients.