← Search

Rui Duan

6 accepted papers

2025

SVA: A Street-View-Aided GNSS Positioning Framework With 2DSDM and Likelihood Road for NLOS/Multipath Mitigation

RA-L 2025

Global Navigation Satellite System (GNSS) suffers severe accuracy degradation in urban environments due to Non-Line-of-Sight (NLOS) and multipath effects. Several methods have been proposed to detect and mitigate NLOS/multipath, but those rely on additional equipment, high costs, and limited multipa

Cited by 2SourceScholar
2024

Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles

NeurIPS 2024poster

Polynomial-based learnable spectral graph neural networks (GNNs) utilize polynomial to approximate graph convolutions and have achieved impressive performance on graphs. Nevertheless, there are three progressive problems to be solved. Some models use polynomials with better approximation for approxi…

Cited by 0SourcePDFScholar
2023

How To Prevent the Poor Performance Clients for Personalized Federated Learning?

CVPR 2023poster

Personalized federated learning (pFL) collaboratively trains personalized models, which provides a customized model solution for individual clients in the presence of heterogeneous distributed local data. Although many recent studies have applied various algorithms to enhance personalization in pFL,…

Cited by 19SourcePDFScholar
2022

Generalized Federated Learning via Sharpness Aware Minimization

ICML 2022spotlight

Federated Learning (FL) is a promising framework for performing privacy-preserving, distributed learning with a set of clients. However, the data distribution among clients often exhibits non-IID, i.e., distribution shift, which makes efficient optimization difficult. To tackle this problem, many FL…

Cited by 182SourcePDFScholar