activity
20182022
most citedSecure Federated Submodel Learning

28 citations · 52 across the 9 of their papers we have counts for

collaborators

12 papers

cs.CV2022

One-Time Model Adaptation to Heterogeneous Clients: An Intra-Client and Inter-Image Attention Design

Yikai Yan, Chaoyue Niu, Fan Wu +4

The mainstream workflow of image recognition applications is first training one global model on the cloud for a wide range of classes and then serving numerous clients, each with h…

cs.IR2022

On-Device Model Fine-Tuning with Label Correction in Recommender Systems

Yucheng Ding, Chaoyue Niu, Fan Wu +3

To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mob…

cs.LG202210 cited

Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning

Chengfei Lv, Chaoyue Niu, Renjie Gu +17

To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system,…

cs.LG20221 cited

On-Device Learning with Cloud-Coordinated Data Augmentation for Extreme Model Personalization in Recommender Systems

Renjie Gu, Chaoyue Niu, Yikai Yan +5

Data heterogeneity is an intrinsic property of recommender systems, making models trained over the global data on the cloud, which is the mainstream in industry, non-optimal to eac…

cs.LG20201 cited

Toward Understanding the Influence of Individual Clients in Federated Learning

Yihao Xue, Chaoyue Niu, Zhenzhe Zheng +4

Federated learning allows mobile clients to jointly train a global model without sending their private data to a central server. Extensive works have studied the performance guaran…

cs.RO2020

Depth estimation on embedded computers for robot swarms in forest

Chaoyue Niu, Danesh Tarapore, Klaus-Peter Zauner

Robot swarms to date are not prepared for autonomous navigation such as path planning and obstacle detection in forest floor, unable to achieve low-cost. The development of depth s…