Dave Zhenyu Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Dave Zhenyu Chen has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Alois Knoll
Technical University of Munich
1 shared publication - Andreas Festag
Technische Hochschule Ingolstadt, CARISSMA Institute for Electric, COnnected, and Secure Mobility (C-ECOS)
1 shared publication - Benjamin Busam
Technical University of Munich
1 shared publication - Carsten Trinitis
Technical University of Munich, Heilbronn, Germany
1 shared publication - Dai Liu
Technical University of Munich
1 shared publication - Evin Pınar Örnek
Technical University of Munich
1 shared publication
Latest Publications
- 26 October 2024
- Published by Springer Nature
- p. 167-184
EchoScene: Indoor Scene Generation via Information Echo Over Scene Graph Diffusion
- 26 October 2024
- Published by Springer Nature
- p. 167-184
EchoScene: Indoor Scene Generation via Information Echo Over Scene Graph Diffusion
- Open Access
Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments
In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks in underlying networks, especially when communicated iteratively. In this paper, we introduce a federated learning framework FedD3 requiring only one-shot communication by integrating dataset distillation instances. Instead of sharing model updates in other federated learning approaches, FedD3 allows the connected clients to distill the local datasets independently, and then aggregates those decentralized distilled datasets (e.g. a few unrecognizable images) from networks for model training. Our experimental results show that FedD3 significantly outperforms other federated learning frameworks in terms of needed communication volumes, while it provides the additional benefit to be able to balance the trade-off between accuracy and communication cost, depending on usage scenario or target dataset. For instance, for training an AlexNet model on CIFAR-10 with 10 clients under non-independent and identically distributed (Non-IID) setting, FedD3 can either increase the accuracy by over 71% with a similar communication volume, or save 98% of communication volume, while reaching the same accuracy, compared to other one-shot federated learning approaches.
Open AccessFederated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments
In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks in underlying networks, especially when communicated iteratively. In this paper, we introduce a federated learning framework FedD3 requiring only one-shot communication by integrating dataset distillation instances. Instead of sharing model updates in other federated learning approaches, FedD3 allows the connected clients to distill the local datasets independently, and then aggregates those decentralized distilled datasets (e.g. a few unrecognizable images) from networks for model training. Our experimental results show that FedD3 significantly outperforms other federated learning frameworks in terms of needed communication volumes, while it provides the additional benefit to be able to balance the trade-off between accuracy and communication cost, depending on usage scenario or target dataset. For instance, for training an AlexNet model on CIFAR-10 with 10 clients under non-independent and identically distributed (Non-IID) setting, FedD3 can either increase the accuracy by over 71% with a similar communication volume, or save 98% of communication volume, while reaching the same accuracy, compared to other one-shot federated learning approaches.