Shilin He （何世林）


Senior Researcher, Microsoft Research

Contact Info:

Email: shilin.he@microsoft.com
 Github     Google Scholar   

 

Introduction:

I am now a Senior researcher in the DKI group at Microsoft. My recent focuses are LLM and its applications, including Agents, RAG, etc. Before that, I worked on AIOps and machine translation.

I joined Microsoft Research Asia in 2020. Prior to that, I received my Ph.D. degree from the Chinese University of Hong Kong (CUHK) in 2020, under the supervision of Prof. Michael R. Lyu.

I am the maintainer of TaskWeaver, a code-first agent framework designed for reliable planning and code execution. I am also the maintainer of LogPAI project, one of the most comprehensive open-source projects in the AIOps area.


 

All Publications

For recent publications, please refer to my Google Scholar

Towards Lightweight, Model-Agnostic and Diversity-Aware Active Anomaly Detection [PDF] [BibTex]
Xu Zhang, Yuan Zhao, Ziang Cui, Liqun Li, Shilin He, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang
ICLR 2023

CONAN: Diagnosing Batch Failures for Cloud Systems [PDF] [BibTex]
Liqun Li, Xu Zhang, Shilin He, Yu Kang, Hongyu Zhang, Minghua Ma, Yingnong Dang, Zhangwei Xu, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang
ICSE-SEIP 2023

Did We Miss Something Important? Studying and Exploring Variable-Aware Log Abstraction [PDF] [BibTex]
Zhenhao Li, Chuan Luo, Tse-Hsun (Peter) Chen, Weiyi Shang, Shilin He, Qingwei Lin, Dongmei Zhang
ICSE 2023

Incident-aware Duplicate Ticket Aggregation for Cloud Systems [PDF] [BibTex]
Jinyang Liu, Shilin He, Zhuangbin Chen, Liqun Li, Yu Kang, Xu Zhang, Pinjia He, Hongyu Zhang, Qingwei Lin, Zhangwei Xu, Saravan Rajmohan, Dongmei Zhang, Michael R Lyu
ICSE 2023

An Empirical Study of Log Analysis at Microsoft [PDF] [BibTex]
Shilin He, Xu Zhang, Pinjia He, Yong Xu, Liqun Li, Yu Kang, Minghua Ma, Yining Wei, Yingnong Dang, Saravan Rajmohan, Qingwei Lin
ESEC/FSE 2022

An Empirical Investigation of Missing Data Handling in Cloud Node Failure Prediction [PDF] [BibTex]
Minghua Ma, Yudong Liu, Yuang Tong, Haozhe Li, Pu Zhao, Yong Xu, Hongyu Zhang, Shilin He, Lu Wang, Yingnong Dang, Saravan Rajmohan, Qingwei Lin
ESEC/FSE 2022

SPINE: A Scalable Log Parser with Feedback Guidance [PDF] [BibTex]
Xuheng Wang, Xu Zhang, Liqun Li, Shilin He, Hongyu Zhang, Yudong Liu, Lingling Zheng, Yu Kang, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang
ESEC/FSE 2022 Distinguished Paper Award

XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation [PDF] [BibTex]
Yong Wang, Shilin He, Guanhua Chen, Yun Chen, Daxin Jiang
EMNLP 2022

UniParser: A Unified Log Parser for Heterogeneous Log Data [PDF] [BibTex]
Yudong Liu, Xu Zhang, Shilin He, Hongyu Zhang, Liqun Li, Yu Kang, Yong Xu, Minghua Ma, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang
The Web Conference (WWW 2022)

Exploiting Inactive Examples for Natural Language Generation with Data Rejuvenation [PDF] [BibTex]
Wenxiang Jiao, Xing Wang, Shilin He, Zhaopeng Tu, Irwin King, Michael R Lyu
IEEE/ACM Transactions on Audio, Speech, and Language Processing 2022

Fighting the Fog of War: Automated Incident Detection for Cloud Systems [PDF] [BibTex]
Liqun Li, Xu Zhang, Xin Zhao, Hongyu Zhang, Yu Kang, Pu Zhao, Bo Qiao, Shilin He, Pochian Lee, Jeffrey Sun, Feng Gao, Li Yang, Qingwei Lin, Saravanakumar Rajmohan, Zhangwei Xu, Dongmei Zhang
2021 USENIX Annual Technical Conference (USENIX ATC 2021)

Onion: Identifying Incident-indicating Logs for Cloud Systems [PDF] [BibTex]
Xu Zhang, Yong Xu, Si Qin, Shilin He, Bo Qiao, Ze Li, Hongyu Zhang, Xukun Li, Yingnong Dang, Qingwei Lin, Murali Chintalapati, Saravanakumar Rajmohan, Dongmei Zhang
ESEC/FSE 2021 Industry Track

Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation [arXiv] [BibTex]
Yongchang Hao, Shilin He, Wenxiang Jiao, Zhaopeng Tu, Michael Lyu, Xing Wang
NAACL 2021

A Survey on Automated Log Analysis for Reliability Engineering [arXiv] [BibTex]
Shilin He, Pinjia He, Zhuangbin Chen, Tianyi Yang, Yuxin Su, Michael R. Lyu
ACM Computing Survey 2021

Loghub: A Large Collection of System Log Datasets towards Automated Log Analytics [arXiv] [BibTex]
Shilin He, Jieming Zhu, Pinjia He, Michael R. Lyu
Arxiv 2020

Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation [arXiv] [BibTex]
Wenxiang Jiao, Xing Wang, Shilin He, Irwin King, Michael R. Lyu, Zhaopeng Tu
EMNLP 2020

Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models [arXiv] [BibTex]
Shilin He, Xing Wang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu
Arxiv 2020

Towards Understanding Neural Machine Translation with Word Importance [arXiv] [BibTex]
Shilin He, Zhaopeng Tu, Xing Wang, Longyue Wang, Michael R. Lyu, Shuming Shi
In Proceedings of the Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP 2019), Hong Kong, Nov 3 - 7, 2019

Logzip: Extracting Hidden Structures via Iterative Clustering for Execution Log Compression [arXiv] [Code] [BibTex]
Jinyang Liu, Jieming Zhu, Shilin He, Pinjia He, Zibin Zheng, Michael R. Lyu
In Proceedings of the The 34th IEEE/ACM International Conference on Automated Software Engineering (ASE 2019), San Diego, United States, Nov 11 - 15, 2019

Tools and Benchmarks for Automated Log Parsing [arXiv] [Code] [BibTex]
Jieming Zhu, Shilin He, Jinyang Liu, Pinjia He, Qi Xie, Zibin Zheng, Michael R. Lyu
In Proceedings of the 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE 2019), Montréal, QC, Canada, May 25 - 31, 2019

Identifying Impactful Service System Problems via Log Analysis [PDF] [Code] [BibTex]
Shilin He, Qingwei Lin, Jian-Guang Lou, Hongyu Zhang, Michael R. Lyu, Dongmei Zhang
In Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering(ESEC/FSE 2018), Lake Buena Vista, FL, USA, Nov 4 - 9, 2018

Characterizing the natural language descriptions in software logging statements [PDF] [Code] [BibTex]
Pinjia He, Zhuangbin Chen, Shilin He, Michael R. Lyu
In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering (ASE 2018), Montpellier, France, Sept 03 - 07, 2018

Towards Automated Log Parsing for Large-scale Log Data Analysis [Journal] [PDF] [BibTex]
Pinjia He, Jieming Zhu, Shilin He, Jian Li, Michael R. Lyu
IEEE Transactions on Dependable and Secure Computing (TDSC) (Volume: 15, Issue: 6, Nov.-Dec. 1, 2018)

Experience Report: System Log Analysis for Anomaly Detection [PDF] [Code] [BibTex]
Shilin He, Jieming Zhu, Pinjia He, Michael R. Lyu
In Proceedings of 2016 IEEE 27th International Symposium on Software Reliability Engineering (ISSRE 2016), Ottawa, Canada, Oct 23-27, 2016
Selected as Most Influential Papers of 30 Years of ISSRE   [Link]

An Evaluation Study on Log Parsing and its Use in Log Mining [PDF] [Code] [BibTex]
Pinjia He, Jieming Zhu, Shilin He, Michael R. Lyu
In Proceedings of 2016 46th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2016), Toulouse, France, Jun 28 - Jul 1, 2016