Shenglin Yin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shenglin Yin has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jieyi Long
Theta Labs, Inc., San Jose, USA
4 shared publications - Zhen Xiao
School of Computer Science, Peking University, Beijing, China
4 shared publications - Bohan Zhou
School of Computer Science, Peking University, Beijing, China
2 shared publications - Mingxuan Song
School of Computer Science, Peking University, Beijing, China
2 shared publications - Chuan Yu
Alibaba Group, Beijing, China
1 shared publication - Hangyu Mao
Kuaishou Technology, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 40-50
DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 40-50
Open AccessDARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 706-716
AERO: Enhancing Sharding Blockchain via Deep Reinforcement Learning for Account Migration
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 706-716
Open AccessAERO: Enhancing Sharding Blockchain via Deep Reinforcement Learning for Account Migration
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 9435-9444
Embracing Adaptation: An Effective Dynamic Defense Strategy Against Adversarial Examples
Existing adversarial example defense methods are static, meaning they remain unchanged once training is completed, regardless of how attack methods change. Consequently, static defense methods are highly vulnerable to adaptive attacks. We argue that to counter more formidable attacks, models should continually adapt to various attack methods. We propose a novel dynamic defense approach. Initially, we use Gaussian Mixture Models (GMM) to obtain structural information of the data, which is combined with model prediction information to generate pseudo-labels for optimizing inputs. Subsequently, we employ information maximization and enhanced mean predictions as optimization objectives, utilizing a hierarchical optimization approach to refine the model. Meanwhile, we propose a sample-efficient optimization strategy that reduces the total number of samples in the test data stream for reverse updating and improves the efficiency. Notably, our method can be directly applied to pre-trained models without the need for accessing training data or retraining the model. Therefore, our approach is training-data-agnostic and model-agnostic, easily applicable to existing adversarially trained models, significantly enhancing the resilience of various models against white-box, black-box, and adaptive attacks across diverse datasets. We have conducted extensive experiments to validate the state-of-the-art of our proposed method. The pseudo-code can be found in the appendix.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 9435-9444
Open AccessEmbracing Adaptation: An Effective Dynamic Defense Strategy Against Adversarial Examples
Existing adversarial example defense methods are static, meaning they remain unchanged once training is completed, regardless of how attack methods change. Consequently, static defense methods are highly vulnerable to adaptive attacks. We argue that to counter more formidable attacks, models should continually adapt to various attack methods. We propose a novel dynamic defense approach. Initially, we use Gaussian Mixture Models (GMM) to obtain structural information of the data, which is combined with model prediction information to generate pseudo-labels for optimizing inputs. Subsequently, we employ information maximization and enhanced mean predictions as optimization objectives, utilizing a hierarchical optimization approach to refine the model. Meanwhile, we propose a sample-efficient optimization strategy that reduces the total number of samples in the test data stream for reverse updating and improves the efficiency. Notably, our method can be directly applied to pre-trained models without the need for accessing training data or retraining the model. Therefore, our approach is training-data-agnostic and model-agnostic, easily applicable to existing adversarially trained models, significantly enhancing the resilience of various models against white-box, black-box, and adaptive attacks across diverse datasets. We have conducted extensive experiments to validate the state-of-the-art of our proposed method. The pseudo-code can be found in the appendix.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2776-2788
A Dual-Agent Scheduler for Distributed Deep Learning Jobs on Public Cloud via Reinforcement Learning
Public cloud GPU clusters are becoming emerging platforms for training distributed deep learning jobs. Under this training paradigm, the job scheduler is a crucial component to improve user experiences, i.e., reducing training fees and job completion time, which can also save power costs for service providers. However, the scheduling problem is known to be NP-hard. Most existing work divides it into two easier sub-tasks, i.e., ordering task and placement task, which are responsible for deciding the scheduling orders of jobs and placement orders of GPU machines, respectively. Due to the superior adaptation ability, learning-based policies can generally perform better than traditional heuristic-based methods. Nevertheless, there are still two main challenges that have not been well-solved. First, most learning-based methods only focus on ordering or placement policy independently, while ignoring their cooperation. Second, the unbalanced machine performances and resource contention impose huge overhead and uncertainty on job duration, but rarely be considered in existing work. To tackle these issues, this paper presents a dual-agent scheduler framework abstracted from the two sub-tasks to jointly learn the ordering and placement policies and make better-informed scheduling decisions. Specifically, we design an ordering agent with a scalable squeeze-and-communicate strategy for better cooperation; for the placement agent, we propose a novel Random Walk Gaussian Process to learn the performance similarities of GPU machines while being aware of the uncertain performance fluctuation. Finally, the dual-agent is jointly optimized with multi-agent reinforcement learning. Extensive experiments conducted on the real-world production cluster trace demonstrate the superiority of our model.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2776-2788
Open AccessA Dual-Agent Scheduler for Distributed Deep Learning Jobs on Public Cloud via Reinforcement Learning
Public cloud GPU clusters are becoming emerging platforms for training distributed deep learning jobs. Under this training paradigm, the job scheduler is a crucial component to improve user experiences, i.e., reducing training fees and job completion time, which can also save power costs for service providers. However, the scheduling problem is known to be NP-hard. Most existing work divides it into two easier sub-tasks, i.e., ordering task and placement task, which are responsible for deciding the scheduling orders of jobs and placement orders of GPU machines, respectively. Due to the superior adaptation ability, learning-based policies can generally perform better than traditional heuristic-based methods. Nevertheless, there are still two main challenges that have not been well-solved. First, most learning-based methods only focus on ordering or placement policy independently, while ignoring their cooperation. Second, the unbalanced machine performances and resource contention impose huge overhead and uncertainty on job duration, but rarely be considered in existing work. To tackle these issues, this paper presents a dual-agent scheduler framework abstracted from the two sub-tasks to jointly learn the ordering and placement policies and make better-informed scheduling decisions. Specifically, we design an ordering agent with a scalable squeeze-and-communicate strategy for better cooperation; for the placement agent, we propose a novel Random Walk Gaussian Process to learn the performance similarities of GPU machines while being aware of the uncertain performance fluctuation. Finally, the dual-agent is jointly optimized with multi-agent reinforcement learning. Extensive experiments conducted on the real-world production cluster trace demonstrate the superiority of our model.
- 1 October 2021
- Published by Elsevier in Computer Networks
- Vol. 197
Intrusion detection for capsule networks based on dual routing mechanism
- 1 October 2021
- Published by Elsevier in Computer Networks
- Vol. 197
Intrusion detection for capsule networks based on dual routing mechanism
- 30 July 2021
- Published by Springer Nature in International Journal of Theoretical Physics
- Vol. 60 (9) , 3396-3403
Authenticable Quantum Scheme for Secret Sharing Based on Local Distinguishability
- 30 July 2021
- Published by Springer Nature in International Journal of Theoretical Physics
- Vol. 60 (9) , 3396-3403
Authenticable Quantum Scheme for Secret Sharing Based on Local Distinguishability