Chuizheng Meng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chuizheng Meng has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Hao Niu
KDDI Research, Inc., Fujimino, Japan
2 shared publications - Yan Liu
University of Southern California, USA
2 shared publications - Chihiro Ono
KDDI Research, Inc., Fujimino, Japan
1 shared publication - Chongyuan Xiang
Pinterest, New York, USA
1 shared publication - Guillaume Habault
KDDI Research, Inc., Fujimino, Japan
1 shared publication - Han Sun
Pinterest, Palo Alto, CA, USA
1 shared publication
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1074-1081
Entity Representation Learning Through Onsite-Offsite Graph for Pinterest Ads
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1074-1081
Open AccessEntity Representation Learning Through Onsite-Offsite Graph for Pinterest Ads
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12703-12714
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12703-12714
Open AccessCoarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1133-1144
Sample-Level Prototypical Federated Learning
With the increasing concerns about privacy and data regulations, federated learning (FL) has been emerging as a solution to train machine learning models collaboratively with non-exchangeable data from multiple clients. As a result of data locality, data is usually not identically or independently (non-IID) distributed across clients, and the non-IID property has long been the key challenge in FL. Furthermore, in real-world cross-silo scenarios, it is ubiquitous that clients are organizations owning private data from multiple domains internally, which exacerbates the non-IID issue. For example, in healthcare applications, each client (hospital) gathers data from patients with heterogeneous demographics. While previous works have made efforts to address the non-IID challenge across clients by assuming various relations among client-level data distributions and enabling personalized models at the client level, they ignore the internal data heterogeneity within each client or require explicit data domain indicators, which are hardly accessible in real-world data. Here, we propose Sample-Level Prototypical Federated Learning (SL-PFL) to bridge the gap. SL-PFL incorporates prototypical learning under the FL framework and provides a fine-grained personalized model for each data sample instead of learning one uniform model for all samples of each client. Meanwhile, it can be trained using data without ground-truth domain indicators. Experimental results demonstrate that our proposed method with sample-level personalized models outperforms existing FL methods with a global model or client-level personalized models on various real-world regression and classification tasks from weather, computer vision, and healthcare applications.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1133-1144
Sample-Level Prototypical Federated Learning
With the increasing concerns about privacy and data regulations, federated learning (FL) has been emerging as a solution to train machine learning models collaboratively with non-exchangeable data from multiple clients. As a result of data locality, data is usually not identically or independently (non-IID) distributed across clients, and the non-IID property has long been the key challenge in FL. Furthermore, in real-world cross-silo scenarios, it is ubiquitous that clients are organizations owning private data from multiple domains internally, which exacerbates the non-IID issue. For example, in healthcare applications, each client (hospital) gathers data from patients with heterogeneous demographics. While previous works have made efforts to address the non-IID challenge across clients by assuming various relations among client-level data distributions and enabling personalized models at the client level, they ignore the internal data heterogeneity within each client or require explicit data domain indicators, which are hardly accessible in real-world data. Here, we propose Sample-Level Prototypical Federated Learning (SL-PFL) to bridge the gap. SL-PFL incorporates prototypical learning under the FL framework and provides a fine-grained personalized model for each data sample instead of learning one uniform model for all samples of each client. Meanwhile, it can be trained using data without ground-truth domain indicators. Experimental results demonstrate that our proposed method with sample-level personalized models outperforms existing FL methods with a global model or client-level personalized models on various real-world regression and classification tasks from weather, computer vision, and healthcare applications.