• Publications
  • Influence
Federated Machine Learning: Concept and Applications
TLDR
We introduce a comprehensive secure federated learning framework, which includes horizontal federatedLearning, vertical federatedlearning and federated transfer learning, and provide a comprehensive survey of existing works on this subject. Expand
  • 316
  • 31
Federated Machine Learning
TLDR
We introduce a comprehensive secure federated-learning framework, which includes horizontal federatedlearning, vertical federated learning, and federated transfer learning. Expand
  • 252
  • 19
  • PDF
SecureBoost: A Lossless Federated Learning Framework
TLDR
In this paper, we propose a novel lossless privacy-preserving tree-boosting system known as SecureBoost in the setting of federated learning. Expand
  • 65
  • 11
  • PDF
Secure Federated Transfer Learning
TLDR
In this paper, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical models under a data federation. Expand
  • 61
  • 10
Learning to Detect Malicious Clients for Robust Federated Learning
TLDR
We propose a framework for robust federated learning where the central server learns to detect and remove the malicious model updates using a powerful detection model, leading to targeted defense. Expand
  • 12
  • 2
  • PDF
A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression
TLDR
We propose a quasi-Newton method based vertical federated learning framework for logistic regression where the data sets at two parties have the same sample IDs but own disjoint subsets of features. Expand
  • 14
  • 2
  • PDF
Backdoor attacks and defenses in feature-partitioned collaborative learning
TLDR
We show that even parties with no access to labels can successfully inject backdoor attacks in the feature-partitioned collaborative learning framework. Expand
  • 6
  • 2
  • PDF
An ankle-foot prosthesis emulator with control of plantarflexion and inversion-eversion torque
TLDR
Ankle inversion-eversion compliance is an important feature of conventional prosthetic feet, and control of inversion, or roll, in robotic prostheses could improve balance for people with amputation. Expand
  • 33
  • 1
  • PDF
FedVision: An Online Visual Object Detection Platform Powered by Federated Learning
TLDR
We report FedVision - a machine learning engineering platform to support the development of federated learning powered computer vision applications. Expand
  • 11
  • 1
  • PDF
Federated Transfer Reinforcement Learning for Autonomous Driving
TLDR
An online federated RL transfer process for real-time knowledge extraction where all the participant agents make corresponding actions with the knowledge learned by others, even when they are acting in very different environments. Expand
  • 12
  • 1
  • PDF