Federated learning ≈ Federated learning
View article
Communication-Efficient Learning of Deep Networks from Decentralized Data Open
Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image …
View article
Advances and Open Problems in Federated Learning Open
Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the tr…
View article
Federated Learning: Strategies for Improving Communication Efficiency Open
Federated Learning is a machine learning setting where the goal is to train a high-quality centralized model while training data remains distributed over a large number of clients each with unreliable and relatively slow network connection…
View article
Federated Learning with Non-IID Data Open
Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model for prediction, while keeping the training data local. This decentralized approach to train models provide…
View article
Federated Optimization: Distributed Machine Learning for On-Device Intelligence Open
We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number of nodes. The goal is to train a high-q…
View article
Federated Learning of Deep Networks using Model Averaging Open
Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image …
View article
Towards Federated Learning at Scale: System Design Open
Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralized data. We have built a scalable production system for Federated Learning in the domain of mobile devices, based on…
View article
How To Backdoor Federated Learning Open
Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards wi…
View article
FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping Open
Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious. The key idea of existing Byzantine-robust federated learning methods is that the servic…
View article
Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification Open
Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly…
View article
Federated Machine Learning: Concept and Applications Open
Today's AI still faces two major challenges. One is that in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secu…
View article
Personalized Cross-Silo Federated Learning on Non-IID Data Open
Non-IID data present a tough challenge for federated learning. In this paper, we explore a novel idea of facilitating pairwise collaborations between clients with similar data. We propose FedAMP, a new method employing federated attentive …
View article
A Secure Federated Transfer Learning Framework Open
Machine learning relies on the availability of a vast amount of data for\ntraining. However, in reality, most data are scattered across different\norganizations and cannot be easily integrated under many legal and practical\nconstraints. I…
View article
Communication-Efficient Federated Deep Learning With Layerwise Asynchronous Model Update and Temporally Weighted Aggregation Open
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 …
View article
SplitFed: When Federated Learning Meets Split Learning Open
Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better mode…
View article
Differentially Private Federated Learning: A Client Level Perspective Open
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, ult…
View article
FedProto: Federated Prototype Learning across Heterogeneous Clients Open
Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space. For example, clients may differ in…
View article
A Comprehensive Survey of Privacy-preserving Federated Learning Open
The past four years have witnessed the rapid development of federated learning (FL). However, new privacy concerns have also emerged during the aggregation of the distributed intermediate results. The emerging privacy-preserving FL (PPFL) …
View article
Federated Learning: Collaborative Machine Learning withoutCentralized Training Data Open
Federated learning (also known as collaborative learning) is a machine learning technique that trains an algorithm without transferring data samples across numerous decentralized edge devices or servers. This strategy differs from standard…
View article
FedMD: Heterogenous Federated Learning via Model Distillation Open
Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own mod…
View article
Applied Federated Learning: Improving Google Keyboard Query Suggestions Open
Federated learning is a distributed form of machine learning where both the training data and model training are decentralized. In this paper, we use federated learning in a commercial, global-scale setting to train, evaluate and deploy a …
View article
Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data Open
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose fede…
View article
Asynchronous Federated Optimization Open
Federated learning enables training on a massive number of edge devices. To improve flexibility and scalability, we propose a new asynchronous federated optimization algorithm. We prove that the proposed approach has near-linear convergenc…
View article
Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption Open
Consider two data providers, each maintaining private records of different feature sets about common entities. They aim to learn a linear model jointly in a federated setting, namely, data is local and a shared model is trained from locall…
View article
Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses for Federated Learning Open
Federated learning (FL) enables many data owners (e.g., mobile devices) to train a joint ML model (e.g., a nextword prediction classifier) without the need of sharing their private training data.However, FL is known to be susceptible to po…
View article
Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks Open
Federated learning (FL) is emerging as a new paradigm to train machine\nlearning models in distributed systems. Rather than sharing, and disclosing,\nthe training dataset with the server, the model parameters (e.g. neural\nnetworks weights…
View article
Analyzing Federated Learning through an Adversarial Lens Open
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this wo…
View article
Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues Open
Federated learning (FL) is a distributed machine learning approach that can achieve the purpose of collaborative learning from a large amount of data that belong to different parties without sharing the raw data among the data owners. FL c…
View article
Hierarchical federated learning across heterogeneous cellular networks Open
We consider federated edge learning (FEEL), where mobile users (MUs) collaboratively learn a global model by sharing local updates on the model parameters rather than their datasets, with the help of a mobile base station (MBS). We optimiz…
View article
Improving Federated Learning Personalization via Model Agnostic Meta Learning Open
Federated Learning (FL) refers to learning a high quality global model based on decentralized data storage, without ever copying the raw data. A natural scenario arises with data created on mobile phones by the activity of their users. Giv…