• Publications
  • Influence
Advances and Open Problems in Federated Learning
TLDR
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, while keeping the training data decentralized. Expand
  • 578
  • 56
  • PDF
Threats to Federated Learning: A Survey
TLDR
We introduce the concept of federated learning (FL) which enables a multitude of participants to construct a joint ML model without exposing their private training data. Expand
  • 43
  • 4
  • PDF
Multi-Participant Multi-Class Vertical Federated Learning
TLDR
In this paper, we propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework for multi-class VFL problems involving multiple parties. Expand
  • 16
  • 2
  • PDF
Surveillance Video Parsing with Single Frame Supervision
TLDR
In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. Expand
  • 33
  • 1
  • PDF
A Fairness-aware Incentive Scheme for Federated Learning
TLDR
In federated learning (FL), data owners "share" their local data in a privacy preserving manner in order to build a federated model, which in turn, can be used to generate revenues for the participants. Expand
  • 30
  • 1
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
  • 21
  • 1
  • PDF
Output Synchronization of Multi-Agent Systems with Event-Driven Communication : Communication Delay and Signal Quantization
In this paper, we study the output synchronization problem o f multi-agent systems with event-driven communication, in which the data transmissions among neighborin g agents are event-based ratherExpand
  • 11
  • 1
  • PDF
FOCUS: Dealing with Label Quality Disparity in Federated Learning
TLDR
We propose Federated Opportunistic Computing for Ubiquitous Systems (FOCUS) to address this challenge. Expand
  • 4
  • 1
  • PDF
The Effect of Public Health Insurance on Criminal Recidivism
We consider a Beckerian enforcement model to identify different channels through which health care access may affect recidivism, and we empirically estimate these effects. By exploiting variation inExpand
  • 4
  • 1
  • PDF
Predicting lncRNA–Protein Interactions With miRNAs as Mediators in a Heterogeneous Network Model
TLDR
A novel way to estimate lncRNA–protein interactions in a heterogeneous network without direct prior knowledge. Expand
  • 4
...
1
2
3
4
5
...