Ziyang Chen

Ziyang Chen

Auto-generated profile, based on publicly available information

Ziyang Chen

Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 February 2026 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
YZYing Zhou
Ying Zhou
ZCZiyang Chen
Ziyang Chen
HAHuilin Ai
Huilin Ai
HXHeng Xu
Heng Xu
CDChengze Du
Chengze Du
JLJialong Li
Jialong Li
Federated learning (FL) is being increasingly adopted in consumer-electronics (CE)-enabled vehicular networks to support privacy-preserving model training. However, the performance of existing FL frameworks significantly degrades under practical heterogeneous conditions, where devices differ in data distribution, computing capabilities, and wireless link quality. To address these challenges, we develop a delay-aware system model that quantifies per-CE computation and communication costs, and formulates a resource-constrained integer programming strategy for CE selection. Building on this model, we propose FedSA-CE, a selection-aware clustering framework tailored for personalized FL in dynamic vehicular environments. FedSA-CE extracts compact CE representations using truncated Singular Value Decomposition (SVD), groups CEs based on cosine similarity, and adaptively selects participants via a contribution– latency objective with time-decaying weighting. The framework prioritizes CEs with rapidly changing gradients in early training phases to accelerate convergence and gradually incorporates more diverse CEs in later stages to enhance generalization while maintaining acceptable waiting time. A similarity-weighted personalized aggregation scheme further improves local model adaptation. Experiments on 4 benchmark datasets demonstrate that FedSA-CE achieves an average accuracy improvement of 24.7% and reduces average waiting time by 83.0% compared with 7 state-of-the-art baselines. Moreover, under all extreme non-independent and identically distributed (Non-IID) settings, FedSA-CE yields an average minimum accuracy gain of 2.92% over the best-performing competing method across all datasets.

15 June 2026
Verified
Conference Paper
Open access
SGShuang Guo
Shuang Guo
YZYing Zhou
Ying Zhou
MSMeina Song
Meina Song
HAHuilin Ai
Huilin Ai
JLJia Long Li
Jia Long Li
ZCZi Yang Chen
Zi Yang Chen

15 June 2026
Verified
Conference Paper
Open access
HAHuilin Ai
Huilin Ai
YZYing Zhou
Ying Zhou
ZPZhonghua Peng
Zhonghua Peng
ZCZiyang Chen
Ziyang Chen
SGShuang Guo
Shuang Guo
JLJialong Li
Jialong Li

19 August 2026 in Journal of Network and Computer Applications
Verified
Journal Article
Closed access
YZYing Zhou
Ying Zhou
ZCZiyang Chen
Ziyang Chen
HAHuilin Ai
Huilin Ai
ZYZhiwei Yu
Zhiwei Yu
HXHeng Xu
Heng Xu
JLJialong Li
Jialong Li