Changlong Ji — accepted AI-conference papers

2025

Re-Evaluating Privacy in Centralized and Decentralized Learning: An Information-Theoretical and Empirical Study

Changlong Ji, Richard Heusdens, Stephane Maag, Qiongxiu Li

ICASSP 2025accepted

Decentralized Federated Learning (DFL) has garnered attention for its robustness and scalability compared to Centralized Federated Learning (CFL). While DFL is commonly believed to offer privacy advantages due to the decentralized control of sensitive data, recent work by Pasquini et, al. challenges…

Cited by 0 Source ↗Scholar ↗

2024

Topology-Dependent Privacy Bound for Decentralized Federated Learning

Qiongxiu Li, Wenrui Yu, Changlong Ji, Richard Heusdens

ICASSP 2024accepted

Decentralized Federated Learning (FL) has attracted significant attention due to its enhanced robustness and scalability compared to its centralized counterpart. It pivots on peer-to-peer communication rather than depending on a central server for model aggregation. While prior research has delved i…

Cited by 0 Source ↗Scholar ↗