activity
20202023
most citedFedKD: Communication Efficient Federated Learning via Knowledge Distillation

623 citations · 795 across the 19 of their papers we have counts for

collaborators
Showing 2022Show all

6 papers · 1 filter

cs.RO2022

Task-Agnostic Adaptation for Safe Human-Robot Handover

Ruixuan Liu, Rui Chen, Changliu Liu

Human-robot interaction (HRI) is an important component to improve the flexibility of modern production lines. However, in real-world applications, the task (\ie the conditions tha…

cond-mat.mes-hall2022★ 55 cited

Quantized anomalous Hall resistivity achieved in molecular beam epitaxy-grown MnBi2Te4 thin films

Yunhe Bai, Yuanzhao Li, Jianli Luan +17

The intrinsic magnetic topological insulator MnBi2Te4 provides a feasible pathway to high temperature quantum anomalous Hall (QAH) effect as well as various novel topological quant…

cs.IR2022★ 2 cited

PrivateRec: Differentially Private Training and Serving for Federated News Recommendation

Ruixuan Liu, Yanlin Wang, Yang Cao +4

Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the prob…

cs.RO2022★ 2 cited

Safe Interactive Industrial Robots using Jerk-based Safe Set Algorithm

Ruixuan Liu, Rui Chen, Changliu Liu

The need to increase the flexibility of production lines is calling for robots to collaborate with human workers. However, existing interactive industrial robots only guarantee int…

cs.CR2022

FLDP: Flexible strategy for local differential privacy

Dan Zhao, Suyun Zhao, Ruixuan Liu +3

Local differential privacy (LDP), a technique applying unbiased statistical estimations instead of real data, is often adopted in data collection. In particular, this technique is…

cs.LG2022★ 90 cited

No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices

Ruixuan Liu, Fangzhao Wu, Chuhan Wu +4

Federated learning (FL) is an important paradigm for training global models from decentralized data in a privacy-preserving way. Existing FL methods usually assume the global model…