Jin Zhong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jin Zhong has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Shuangping Huang
South China University of Technology, Guangzhou, China
3 shared publications - Gang Dai
South China University of Technology
2 shared publications - Hanlin Gu
Webank, Shenzhen, China
2 shared publications - Jinglin Liang
South China University of Technology
2 shared publications - Lixin Fan
WeBank
2 shared publications - Qiang Yang
The Hong Kong Polytechnic University, Hong Kong, Hong Kong
2 shared publications
Latest Publications
- 30 October 2024
- Published by Springer Nature
- p. 303-319
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
- 30 October 2024
- Published by Springer Nature
- p. 303-319
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
- Open Access
Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue that has been explored to some extent in Continual Learning (CL). However, due to privacy preservation requirements, some conventional methods, such as experience replay, are not directly applicable to FCCL. Existing FCCL methods mitigate forgetting by generating historical data through federated training of GANs or data-free knowledge distillation. However, these approaches often suffer from unstable training of generators or low-quality generated data, limiting their guidance for the model. To address this challenge, we propose a novel method of data replay based on diffusion models. Instead of training a diffusion model, we employ a pre-trained conditional diffusion model to reverse-engineer each class, searching the corresponding input conditions for each class within the model's input space, significantly reducing computational resources and time consumption while ensuring effective generation. Furthermore, we enhance the classifier's domain generalization ability on generated and real data through contrastive learning, indirectly improving the representational capability of generated data for real data. Comprehensive experiments demonstrate that our method significantly outperforms existing baselines. Code is available at https://github.com/jinglin-liang/DDDR.
Open AccessDiffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue that has been explored to some extent in Continual Learning (CL). However, due to privacy preservation requirements, some conventional methods, such as experience replay, are not directly applicable to FCCL. Existing FCCL methods mitigate forgetting by generating historical data through federated training of GANs or data-free knowledge distillation. However, these approaches often suffer from unstable training of generators or low-quality generated data, limiting their guidance for the model. To address this challenge, we propose a novel method of data replay based on diffusion models. Instead of training a diffusion model, we employ a pre-trained conditional diffusion model to reverse-engineer each class, searching the corresponding input conditions for each class within the model's input space, significantly reducing computational resources and time consumption while ensuring effective generation. Furthermore, we enhance the classifier's domain generalization ability on generated and real data through contrastive learning, indirectly improving the representational capability of generated data for real data. Comprehensive experiments demonstrate that our method significantly outperforms existing baselines. Code is available at https://github.com/jinglin-liang/DDDR.
- Open Access
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Nash equilibria of two-round auctions
In a two-round auction, a subset of bidders is selected (probabilistically), according to their bids in the first round, for the second round, where they can increase their bids. We formalize the two-round auction model, restricting the second round to a dominant strategy incentive compatible (DSIC) auction for the selected bidders. It turns out that, however, such two-round auctions are not directly DSIC, even if the probability of each bidder being selected for the second round is monotonic to its first bid, which is surprisingly counter-intuitive. We also illustrate the necessary and sufficient conditions of two-round auctions being DSIC. Besides, we characterize the Nash equilibria for untruthful two-round auctions. One can achieve better revenue performance by setting proper probability for selecting bidders for the second round compared with single-round auctions.
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessNash equilibria of two-round auctions
In a two-round auction, a subset of bidders is selected (probabilistically), according to their bids in the first round, for the second round, where they can increase their bids. We formalize the two-round auction model, restricting the second round to a dominant strategy incentive compatible (DSIC) auction for the selected bidders. It turns out that, however, such two-round auctions are not directly DSIC, even if the probability of each bidder being selected for the second round is monotonic to its first bid, which is surprisingly counter-intuitive. We also illustrate the necessary and sufficient conditions of two-round auctions being DSIC. Besides, we characterize the Nash equilibria for untruthful two-round auctions. One can achieve better revenue performance by setting proper probability for selecting bidders for the second round compared with single-round auctions.