PhD candidate, School of Computer Science, Wuhan UniversityI am Tiangang Li, I am currently working toward the Ph.D. degree in computer science with Wuhan University under the supervision of Prof. Shi Ying. My research interests include Reinforcement Learning, ML for Systems/AIOps, ML/LLM Systems, Distributed Systems and Cloud Computing.
Action required
Problem: The current root path of this site is "baseurl ("/tiangangli.github.io") configured in _config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Wuhan UniversitySchool of Computer Science
Ph.D. Student in Computer ScienceSep. 2021 - present -
Wuhan Research Institute of Posts and TelecommunicationsM.S. in Communications and Information SystemsSep. 2018 - Apr. 2021 -
Wuhan University of TechnologyB.S. in Electronic Information EngineeringSep. 2014 - Jul. 2018
Honors & Awards
-
Rank 33/1681 in CVPR 2021 competition of white-box adversarial attacks on ML defense models2021
Academic Service
-
Assistant to the Chair of CCF ChinaSoft 2021 & 2022 — Exchange and Competition on Teaching Cases in Software2021 & 2022
-
Reviewer for Information Sciences (INS)2025 - 2026
News
Selected Publications (view all )
CRFD: Causal and Interpretable Fault Diagnosis Using Counterfactual Reasoning for Microservices on Multi-source Observability Data
Xiangbo Tian, Shi Ying, Tiangang Li, Chuan Shi, Ding Xiao
ACM Transactions on Software Engineering and Methodology (TOSEM) 2026 JournalCCF-A
We propose CRFD, a causal and interpretable fault diagnosis approach based on multi-source observability data for microservice systems, which uses counterfactual reasoning to diagnose faults and provide effective guidance for subsequent troubleshooting.
CRFD: Causal and Interpretable Fault Diagnosis Using Counterfactual Reasoning for Microservices on Multi-source Observability Data
Xiangbo Tian, Shi Ying, Tiangang Li, Chuan Shi, Ding Xiao
ACM Transactions on Software Engineering and Methodology (TOSEM) 2026 JournalCCF-A
We propose CRFD, a causal and interpretable fault diagnosis approach based on multi-source observability data for microservice systems, which uses counterfactual reasoning to diagnose faults and provide effective guidance for subsequent troubleshooting.
CausalLog: Log parsing using LLMs with causal intervention for bias mitigation
Yuan Tian, Shi Ying, Tiangang Li
Information Processing & Management (IPM) 2024 JournalCCF-A
We propose CausalLog, a lightweight and flexible debiasing framework for log parsing.
CausalLog: Log parsing using LLMs with causal intervention for bias mitigation
Yuan Tian, Shi Ying, Tiangang Li
Information Processing & Management (IPM) 2024 JournalCCF-A
We propose CausalLog, a lightweight and flexible debiasing framework for log parsing.
DALAD: Unsupervised Detection of Global and Local Anomalies in Microservice Systems
Xiangbo Tian, Shi Ying, Tiangang Li, Ting Zhang, Yong Wang
IEEE Transactions on Services Computing (TSC) 2025 JournalCCF-A
We propose DALAD, a novel distribution-adversarial-learning-based anomaly detection approach for microservice systems.
DALAD: Unsupervised Detection of Global and Local Anomalies in Microservice Systems
Xiangbo Tian, Shi Ying, Tiangang Li, Ting Zhang, Yong Wang
IEEE Transactions on Services Computing (TSC) 2025 JournalCCF-A
We propose DALAD, a novel distribution-adversarial-learning-based anomaly detection approach for microservice systems.
ASTRA: Adversarial Sim-to-Real Transfer Reinforcement Learning for Autoscaling in Cloud Systems
Tiangang Li, Shi Ying, Xiangbo Tian, Ting Zhang, Yong Wang
IEEE Transactions on Software Engineering (TSE) 2025 JournalCCF-A
We propose ASTRA, a sim-to-real transfer reinforcement learning framework for autoscaling.
ASTRA: Adversarial Sim-to-Real Transfer Reinforcement Learning for Autoscaling in Cloud Systems
Tiangang Li, Shi Ying, Xiangbo Tian, Ting Zhang, Yong Wang
IEEE Transactions on Software Engineering (TSE) 2025 JournalCCF-A
We propose ASTRA, a sim-to-real transfer reinforcement learning framework for autoscaling.
SAC-based Ensemble Framework for Multi-view Workload Forecasting in Cloud Computing
Wenxuan Zeng, Shi Ying, Tiangang Li, Xiangbo Tian, Yuhong Jiang, Hujie Liu, Shikui Hao
Journal of Software (in Chinese) 2025 JournalChinese CCF-A
We propose SAC-MWF, a multi-view workload forecast ensemble framework based on Soft Actor-Critic (SAC) algorithm.
SAC-based Ensemble Framework for Multi-view Workload Forecasting in Cloud Computing
Wenxuan Zeng, Shi Ying, Tiangang Li, Xiangbo Tian, Yuhong Jiang, Hujie Liu, Shikui Hao
Journal of Software (in Chinese) 2025 JournalChinese CCF-A
We propose SAC-MWF, a multi-view workload forecast ensemble framework based on Soft Actor-Critic (SAC) algorithm.
DebiasParser: Debiasing LLM-Based Log Parsing via Front-Door Adjustment
Yuan Tian, Shi Ying, Tiangang Li
International Conference on Intelligent Computing (ICIC) 2025 ConferenceCCF-C
We propose DebiasParser, a novel log parsing framework that incorporates a debiasing mechanism grounded in Structural Causal Models (SCMs) and implemented via front-door adjustment.
DebiasParser: Debiasing LLM-Based Log Parsing via Front-Door Adjustment
Yuan Tian, Shi Ying, Tiangang Li
International Conference on Intelligent Computing (ICIC) 2025 ConferenceCCF-C
We propose DebiasParser, a novel log parsing framework that incorporates a debiasing mechanism grounded in Structural Causal Models (SCMs) and implemented via front-door adjustment.
iTCRL: Causal-Intervention-Based Trace Contrastive Representation Learning for Microservice Systems
Xiangbo Tian, Shi Ying, Tiangang Li, Mengting Yuan, Ruijin Wang, Yishi Zhao
IEEE Transactions on Software Engineering (TSE) 2024 JournalCCF-A
We propose iTCRL, a novel trace contrastive representation learning approach based on causal intervention.
iTCRL: Causal-Intervention-Based Trace Contrastive Representation Learning for Microservice Systems
Xiangbo Tian, Shi Ying, Tiangang Li, Mengting Yuan, Ruijin Wang, Yishi Zhao
IEEE Transactions on Software Engineering (TSE) 2024 JournalCCF-A
We propose iTCRL, a novel trace contrastive representation learning approach based on causal intervention.
Batch Jobs Load Balancing Scheduling in Cloud Computing Using Distributional Reinforcement Learning
Tiangang Li, Shi Ying, Yishi Zhao, Jianga Shang
IEEE Transactions on Parallel and Distributed (TPDS) 2024 JournalCCF-A
We propose a Distributional Reinforcement Learning–based dynamic load balancing algorithm for cloud batch job scheduling, which outperforms existing baselines in load balance, task success rate, and completion time on real Alibaba cluster traces.
Batch Jobs Load Balancing Scheduling in Cloud Computing Using Distributional Reinforcement Learning
Tiangang Li, Shi Ying, Yishi Zhao, Jianga Shang
IEEE Transactions on Parallel and Distributed (TPDS) 2024 JournalCCF-A
We propose a Distributional Reinforcement Learning–based dynamic load balancing algorithm for cloud batch job scheduling, which outperforms existing baselines in load balance, task success rate, and completion time on real Alibaba cluster traces.
Adversarial examples attack based on random warm restart mechanism and improved Nesterov momentum
arXiv 2021 Preprint
We propose RWR-NM-PGD attack algorithm based on random warm restart mechanism and improved Nesterov momentum from the view of gradient optimization.
Adversarial examples attack based on random warm restart mechanism and improved Nesterov momentum
arXiv 2021 Preprint
We propose RWR-NM-PGD attack algorithm based on random warm restart mechanism and improved Nesterov momentum from the view of gradient optimization.