arXiv research

Flexible device participation improves federated learning convergence.

FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.

Federated learning enables a large amount of edge computing devices to jointly learn a model without data sharing. As a leading algorithm in this setting, Federated Averaging (\texttt{FedAvg}) runs Stochastic Gradient Descent (SGD) in parallel on a small subset of the total devices and averages the sequences only once …

Unified analysis of Federated Averaging and Nesterov FedAvg for linear speedup.

Artemis framework improves distributed learning with bidirectional compression and partial participation.

New algorithm reduces communication time in federated learning.

Paper proposes incentive mechanism to encourage participation in federated learning.

Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, a…

Federated learning (FL) rests on the notion of training a global model in a decentralized manner. Under this setting, mobile devices perform computations on their local data before uploading the required updates to improve the global model. However, when the participating clients implement an uncoordinated computation …

Decentralized machine learning is a promising emerging paradigm in view of global challenges of data ownership and privacy. We consider learning of linear classification and regression models, in the setting where the training data is decentralized over many user devices, and the learning algorithm must run on-device, …

Study quantifies impacts of heterogeneity in FL on smartphone data.

A new method for efficient online federated learning reduces communication overhead.

Personalized stress model using transfer learning from 20 participants.

Data poisoning attacks can severely degrade FL models, especially targeting specific classes.

FedDANE adapts DANE for federated learning, but underperforms compared to existing methods.

New optimization for federated learning with local models.

Federated Learning (FL) systems are gaining popularity as a solution to training Machine Learning (ML) models from large-scale user data collected on personal devices (e.g., smartphones) without their raw data leaving the device. At the core of FL is a network of anonymous user devices sharing training information (mod…

On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a central entity. However, for privacy guarantee, it is inevitable at each device to compensate for the quality of data or learning performanc…

This paper tackles computational bottlenecks in federated learning on mobile devices.

New algorithm improves fairness and robustness in federated learning.

Paper optimizes FL communication efficiency with stochastic optimization.

This paper studies communication efficiency in federated learning by optimizing the sum-rate-distortion function for indirect multiterminal source coding.

Federated Learning is a distributed learning paradigm with two key challenges that differentiate it from traditional distributed optimization: (1) significant variability in terms of the systems characteristics on each device in the network (systems heterogeneity), and (2) non-identically distributed data across the ne…

DeepBeat uses deep learning to assess signal quality and detect arrhythmia in wearable devices.

New federated learning methods improve model performance on non-IID data.

AAggFF improves federated learning fairness through sequential decision making.

More frequent model updates in FL increase generalization error.

This paper surveys techniques to personalize federated learning models.

Neural network training entails heavy computation with obvious bottlenecks. The Compute Unified Device Architecture (CUDA) programming model allows us to accelerate computation by passing the processing workload from the CPU to the graphics processing unit (GPU). In this paper, we leveraged the power of Nvidia GPUs to …

The high cost of communicating gradients is a major bottleneck for federated learning, as the bandwidth of the participating user devices is limited. Existing gradient compression algorithms are mainly designed for data centers with high-speed network and achieve $O(\sqrt{d} \log d)$ per-iteration communication cost at…

The future Internet of Things (IoT) will have a deep economical, commercial and social impact on our lives. The participating nodes in IoT networks are usually resource-constrained, which makes them luring targets for cyber attacks. In this regard, extensive efforts have been made to address the security and privacy is…

Federated learning (FL) is a distributed deep learning method which enables multiple participants, such as mobile phones and IoT devices, to contribute a neural network model while their private training data remains in local devices. This distributed approach is promising in the edge computing system where have a larg…

A novel incentive mechanism improves fairness and participation in federated learning.

Optimizes capital structure for life insurance companies with surplus participation.

Paper proposes MMVFL for multi-class VFL with multiple participants.

The paper uncovers two key laws of market impact influenced by volume and participation rate.

Federated learning uses worst-case optimization to handle uncertain local data impacts.

Local adaptation improves federated learning models.

Unified analysis of FL with arbitrary client participation.

Deep learning identifies unknown IoT devices in network traffic.

On-device federated learning updates edge models by exchanging trained results.

Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client;…

Semi-Federated Learning clusters clients for efficient model training.

A method for trust evaluation of devices in human-device coexistence systems.

Two approaches scale up DNN optimization for diverse edge devices.

Web-based framework detects Parkinson's disease from speech recordings.

FedAMD framework improves federated learning with partial client participation.

This paper optimizes how deep learning models are distributed across different devices.