Computer Science Machine Learning

GUINENG ZHENG

*** * ********** **. ***. *, Salt Lake City, Utah, 84102

+1-801******* ******@*****.*** ****@*******.*** *******@**.****.*** EDUCATION

University of Utah August 2018 - Present

Ph.D. Student in Computer Science

Data Group, School of Computing

Advisor: Prof. Vivek Srikumar, Prof. Robert Ricci

University of Utah August 2015 - March 2018

Master Student in Computer Science

Data Group, School of Computing

Advisor: Feifei Li

Nanjing University of Aeronautics and Astronautics August 2005 - March 2012 B.S. & M.S. in Computer Science

Database Group, College of Computer Science and Technology Advisor: Prof. Xiaolin Qin

SKILLS

Python: My main language skill. More than 10 years experience. Java: My main language skill. More than 10 years experience. Machine Learning: My current focusing research. More than 5 years of experience of machine learning techniques including pytorch, tensorflow, sklearn. Very familiar with Natural Language Processing and Computer Vision.

Big Data: Platform Builder of Hadoop, Hive and Spark within Alibaba Cloud. Over 10 years of experience of using raw map reduce job, declarative language of SQL and Spark distributed lambda calculator.

OPEN SOURCE PROJECT

Logflux: https://github.com/logflux/logflux

PUBLICATIONS

Logflux: A Collection Of Automated Log Parsing Tools. ACM REP Guineng Zheng, Robert Ricci and Vivek Srikumar

Opentag: Open attribute value extraction from product profiles. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1049-1058. 2018. Zheng, Guineng and Mukherjee, Subhabrata and Dong, Xin Luna and Li, Feifei Deeplog: Anomaly detection and diagnosis from system logs through deep learning. In Proceedings of the 2017 ACM SIGSAC conference on computer and communications security, pp. 1285-1298. 2017. Du, Min, Feifei Li, Guineng Zheng, and Vivek Srikumar. Adaptive spatial window aggregation query processing algorithm in wireless sensor networks. Interna- tional Journal of Sensor Networks 16, no. 3 (2014): 127-147. Liu, Liang, Xiaolin Qin, Guineng Zheng, and Bohan Li. Reliable spatial window aggregation query processing algorithm in wireless sensor networks. Journal of Network and Computer Applications 35, no. 5 (2012): 1537-1547. Liu, Liang, Xiao-Lin Qin, and Gui-Neng Zheng.

Energy-efficient and robust spatial window aggregation Query processing algorithm in wireless sensor networks. In 2012 32nd International Conference on Distributed Computing Systems Workshops, pp. 169-177. IEEE, 2012.

Liu, Liang, Xiaolin Qin, Bohan Li, Yulei Liu, and Guineng Zheng. An energy-efficient spatial window query processing algorithm in wireless sensor networks. Jisuanji Xuebao(Chinese Journal of Computers) 34, no. 5 (2011): 761-778. Liu, Liang, Xiao-Lin Qin, Gui-Neng Zheng, and Bo-Han Li. SQRM: An effective solution to suspicious users in database. DBKDA 2011, p.59. Hua, D., Xiaolin, Q., Guineng, Z. and Ziyue, L.

EXPERIENCE

University of Utah August 2018 - Present

Ph.D. Candidate

· Machine Learning, Log Template Extraction

University of Utah August 2015 - March 2018

Master

· Big data, Database

Amazon Product Graph August 2017 - December 2017

Fall Research Intern

· Mining attribute of products for Product Graph project NEC Laboratories May 2016 - August 2016

Summer Research Intern

· Designed and implemented the distributed real-time online stream platform which processes over 10K messages per second for the security audit.

China Merchants Bank November 2014 - July 2015

Software Engineer

· In charge of Hadoop clusters of over 100 nodes to support over 50 TB data processing per day.

· Designed and implemented distributed complex event streaming system to support online real-time user auditing for over 30 million users from scratch. I contributed most of the core code for version 1.0. Alibaba Cloud April 2012 - October 2014

Software Engineer

· Hack hive module to add new query optimization to Open Data Processing System which is a self- developed hive in Alibaba

· Profiled the cluster. Invented an algorithm to learn patterns from historical data and constructed an optimizing strategy that gains a 35% performance speedup based on learned patterns.

Contact this candidate