Dr. Weiwei Cheng   程蔚蔚

Senior Machine Learning Scientist at Amazon







What's New | Short Bio | Education | Publications | Patents | Talks & Tutorials | Honors & Awards | Some Links





What's New

previous news


Short Bio

Weiwei Cheng got a double bachelor's degree in Computer Science and Business Administration in June 2004 at Zhengzhou University, China. After graduation, he went to Germany and studied Data and Knowledge Engineering at Otto von Guericke University Magdeburg from October 2005 to November 2007. In October 2006 he was awarded the Outstanding International Student Scholarship by the Ministry of Education and Cultural Affairs of Saxony-Anhalt. He received his Master of Science degree with the highest honor in November 2007 and was awarded as the Best Graduate of Year in October 2008. Since December 2007, he worked as a research staff member in the Computational Intelligence Group at Philipps University Marburg, where he got the doctorate, Dr. rer. nat., in May 2012. He joined Amazon in July 2013, first as a scientist and then a senior scientist in October 2017. His research won several awards, including the Artificial Intelligence Journal Prominent Paper 2015, the Best Paper at the 21st International Conference on Case-Based Reasoning, the Machine Learning Journal Best Student Paper at the 19th European Conference on Machine Learning, etc. He was a recipient of 2009 Chinese Government Award for Outstanding Self-Financed Students Abroad.

My everyday work is to analyze and understand the data around us. I conduct research in multiple areas of artificial intelligence, especially machine learning and natural language processing. My current interests include preference learning, keyphrase extraction, and multi-label classification. I have published a number of scientific papers in related fields and served as PC member and reviewer for many renowned journals and conferences.
curriculum vitae


Education

2007-2012 PhD in Computer Science (Dr. rer. nat.) Chinese government award
Philipps University Marburg, Germany
2005-2007 MS in Computer Science with highest distinction + best graduate award
Otto von Guericke University Magdeburg, Germany
2002-2004 BS in Business Administration
Zhengzhou University, China
2000-2004 BS in Computer Science
Zhengzhou University, China


Publications

Nedelina Teneva, Weiwei Cheng
Salience rank: efficient keyphrase extraction with topic modeling [pdf][bibtex][poster]
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL-17), Vol. 2: 530-535, ACL
Vancouver, Canada, July 2017

Eyke Hüllermeier, Weiwei Cheng
Superset learning based on generalized loss minimization [pdf][bibtex]
LNAI 9285 Machine Learning and Knowledge Discovery in Databases: 260-275, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-15)
Porto, Portugal, September 2015

Róbert Busa-Fekete, Balázs Szörényi, Paul Weng, Weiwei Cheng, Eyke Hüllermeier
Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm [pdf][bibtex]
Machine Learning 97: 327-351, Springer

Willem Waegeman, Krzysztof Dembczyński, Arkadiusz Jachnik, Weiwei Cheng, Eyke Hüllermeier
On the Bayes-optimality of F-measure maximizers [pdf][bibtex]
Journal of Machine Learning Research 15: 3333-3388, Microtome Publishing

Weiwei Cheng, Sascha Henzgen, Eyke Hüllermeier
Labelwise versus pairwise decomposition in label ranking [pdf][bibtex]
Proceedings of Lernen-Wissen-Adaptivität 2013 (LWA-13): 129-136, Otto Friedrich University Bamberg
Bamberg, Germany, October 2013

Weiwei Cheng, Eyke Hüllermeier
A nearest neighbor approach to label ranking based on generalized labelwise loss minimization [pdf][bibtex][slides]
Proceedings of the 7th Multidisciplinary Workshop on Advances in Preference Handling (M-PREF-13)
The 23rd International Joint Conference on Artificial Intelligence (IJCAI-13)
Beijing, China, August 2013

Eyke Hüllermeier, Weiwei Cheng
Preference-based CBR: general ideas and basic principles [pdf][bibtex][slides]
Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI-13): 3012-3016, AAAI Press
Beijing, China, August 2013 invited paper

Amira Abdel-Aziz, Weiwei Cheng, Marc Strickert, Eyke Hüllermeier
Preference-based CBR: a search-based problem solving framework [pdf][bibtex][slides]
LNAI 7969 Case-Based Reasoning Research and Development: 1-14, Springer
The 21st International Conference on Case-Based Reasoning (ICCBR-13)
Saratoga Springs, USA, July 2013 best paper award

Dominik Heider, Robin Senge, Weiwei Cheng, Eyke Hüllermeier
Multilabel classification for exploiting cross-resistance information in HIV-1 drug resistance prediction [pdf][bibtex]
Bioinformatics 29: 1946-1952, Oxford University Press

Róbert Busa-Fekete, Balázs Szörényi, Paul Weng, Weiwei Cheng, Eyke Hüllermeier
Top-k selection based on adaptive sampling of noisy preferences [pdf][bibtex][slides][poster]
Proceedings of the 30th International Conference on Machine Learning (ICML-13): 1094-1102, Microtome Publishing
Atlanta, USA, June 2013

Róbert Busa-Fekete, Balázs Szörényi, Paul Weng, Weiwei Cheng, Eyke Hüllermeier
Preference-based evolutionary direct policy search [pdf][bibtex][poster]
Workshop Proceedings of Autonomous Learning 2013 (AL-13)
IEEE International Conference on Robotics and Automation (ICRA-13)
Karlsruhe, Germany, May 2013

Weiwei Cheng, Eyke Hüllermeier, Willem Waegeman, Volkmar Welker
Label ranking with partial abstention based on thresholded probabilistic models [pdf][bibtex][poster]
Advances in Neural Information Processing Systems 25 (NIPS-12): 2510-2518, Curran Associates
Lake Tahoe, USA, December 2012

Ali Fallah Tehrani, Weiwei Cheng, Eyke Hüllermeier
Preference learning using the Choquet integral: the case of multipartite ranking [pdf][bibtex]
IEEE Transactions on Fuzzy Systems 20: 1102-1113, IEEE Computational Intelligence Society

Weiwei Cheng, Eyke Hüllermeier
Probability estimation for multi-class classification based on label ranking [pdf][bibtex][slides]
LNAI 7524 Machine Learning and Knowledge Discovery in Databases: 83-98, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-12)
Bristol, UK, September 2012

Weiwei Cheng, Krzysztof Dembczyński, Eyke Hüllermeier, Adrian Jaroszewicz, Willem Waegeman
F-measure maximization in topical classification [pdf][bibtex]
LNAI 7413 Rough Sets and Current Trends in Computing: 422-431, Springer
Joint Rough Set Symposium (JRS-12)
Chengdu, China, August 2012 invited paper of JRS 2012 Data Mining Competition

Ali Fallah Tehrani, Weiwei Cheng, Krzysztof Dembczyński, Eyke Hüllermeier
Learning monotone nonlinear models using the Choquet integral [pdf][bibtex]
Machine Learning 89: 183-211, Springer selected paper (7 out of 599) from ECMLPKDD-11

Johannes Fürnkranz, Eyke Hüllermeier, Weiwei Cheng, Sang-Hyeun Park
Preference-based reinforcement learning: a formal framework and a policy iteration algorithm [pdf][bibtex]
Machine Learning 89: 123-156, Springer selected paper (7 out of 599) from ECMLPKDD-11

Krzysztof Dembczyński, Willem Waegeman, Weiwei Cheng, Eyke Hüllermeier
On label dependence and loss minimization in multi-label classification [pdf][bibtex]
Machine Learning 88: 5-45, Springer listed in Notable Computing Books and Articles 2012 by ACM Computing Reviews

Weiwei Cheng
Label ranking with probabilistic models
Doctoral thesis
Faculty of Mathematics and Computer Science, Philipps University Marburg
Marburg, Germany, May 2012 magna cum laude

Krzysztof Dembczyński, Willem Waegeman, Weiwei Cheng, Eyke Hüllermeier
An exact algorithm for F-measure maximization [pdf][bibtex][poster]
Advances in Neural Information Processing Systems 24 (NIPS-11): 223-230, Curran Associates
Granada, Spain, December 2011 NIPS travel grant

Weiwei Cheng, Eyke Hüllermeier
Label ranking with abstention: predicting partial orders by thresholding probability distributions [pdf][bibtex][slides][video]
Workshop Proceedings of Choice Models and Preference Learning 2011 (CMPL-11)
The 25th Annual Conference on Neural Information Processing Systems (NIPS-11)
Sierra Nevada, Spain, December 2011 NIPS travel grant

Thomas Fober, Weiwei Cheng, Eyke Hüllermeier
Focusing search in multiobjective evolutionary optimization through preference learning from user feedback [pdf][bibtex][slides]
Proceedings of the 21st Workshop Computational Intelligence (WCI-11): 107-117, KIT Scientific Publishing
Dortmund, Germany, December 2011

Weiwei Cheng, Gjergji Kasneci, Thore Graepel, David Stern, Ralf Herbrich
Automated feature generation from structured knowledge [pdf][bibtex][slides]
Proceedings of the 20th ACM Conference on Information and Knowledge Management (CIKM-11): 1395-1404, ACM
Glasgow, UK, October 2011

Ali Fallah Tehrani, Weiwei Cheng, Krzysztof Dembczyński, Eyke Hüllermeier
Learning monotone nonlinear models using the Choquet integral [pdf][bibtex][slides][poster][video]
LNAI 6913 Machine Learning and Knowledge Discovery in Databases: 414-429, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-11)
Athens, Greece, September 2011 invited to Machine Learning Journal Special Issue

Weiwei Cheng, Johannes Fürnkranz, Eyke Hüllermeier, Sang-Hyeun Park
Preference-based policy iteration: leveraging preference learning for reinforcement learning [pdf][bibtex][slides]
LNAI 6911 Machine Learning and Knowledge Discovery in Databases: 312-327, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-11)
Athens, Greece, September 2011 invited to Machine Learning Journal Special Issue

Ali Fallah Tehrani, Weiwei Cheng, Eyke Hüllermeier
Choquistic regression: generalizing logistic regression using the Choquet integral [pdf][bibtex][slides]
Proceedings of the 7th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-2011): 868-875, Atlantis Press
Aix-les-Bains, France, July 2011 nominated for best student paper award

Ali Fallah Tehrani, Weiwei Cheng, Eyke Hüllermeier
Preference learning using the Choquet integral: the case of multipartite ranking [pdf][bibtex]
Proceedings of the 20th Workshop Computational Intelligence (WCI-10): 119-130, KIT Scientific Publishing
Dortmund, Germany, December 2010

Weiwei Cheng, Michaël Rademaker, Bernard De Baets, Eyke Hüllermeier
Predicting partial orders: ranking with abstention [pdf][bibtex][slides][poster]
LNAI 6321 Machine Learning and Knowledge Discovery in Databases: 215-230, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-10)
Barcelona, Spain, September 2010 UNESCO ECMLPKDD conference grant

Krzysztof Dembczyński, Willem Waegeman, Weiwei Cheng, Eyke Hüllermeier
Regret analysis for performance metrics in multi-label classification: the case of Hamming and subset zero-one loss [pdf][bibtex][slides][poster]
LNAI 6321 Machine Learning and Knowledge Discovery in Databases: 280-295, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-10)
Barcelona, Spain, September 2010 UNESCO ECMLPKDD conference grant

Krzysztof Dembczyński, Willem Waegeman, Weiwei Cheng, Eyke Hüllermeier
On label dependence in multi-label classification [pdf][bibtex][slides]
Workshop Proceedings of Learning from Multi-Label Data 2010 (MLD-10): 5-12
The 27th International Conference on Machine Learning (ICML-10)
Haifa, Israel, June 2010 invited paper

Weiwei Cheng, Krzysztof Dembczyński, Eyke Hüllermeier
Label ranking methods based on the Plackett-Luce model [pdf][bibtex][slides][poster]
Proceedings of the 27th International Conference on Machine Learning (ICML-10): 215-222, Omnipress
Haifa, Israel, June 2010 ICML scholarship

Weiwei Cheng, Krzysztof Dembczyński, Eyke Hüllermeier
Graded multi-label classification: the ordinal case [pdf][bibtex][slides][poster]
Proceedings of the 27th International Conference on Machine Learning (ICML-10): 223-230, Omnipress
Haifa, Israel, June 2010 ICML scholarship

Krzysztof Dembczyński, Weiwei Cheng, Eyke Hüllermeier
Bayes optimal multi-label classification via probabilistic classifier chains [pdf][bibtex][poster]
Proceedings of the 27th International Conference on Machine Learning (ICML-10): 279-286, Omnipress
Haifa, Israel, June 2010 ICML scholarship

Weiwei Cheng, Eyke Hüllermeier
Label ranking with partial abstention using ensemble learning [pdf][bibtex][slides][video]
Workshop Proceedings of Preference Learning 2009 (PL-09): 17-23
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-09)
Bled, Slovenia, September 2009

Weiwei Cheng, Eyke Hüllermeier
A simple instance-based approach to multi-label classification using the Mallows model [pdf][bibtex][slides]
Workshop Proceedings of Learning from Multi-Label Data 2009 (MLD-09): 28-38
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-09)
Bled, Slovenia, September 2009

Weiwei Cheng, Eyke Hüllermeier
Combining instance-based learning and logistic regression for multi-label classification [pdf][bibtex][slides][poster][video][code]
Machine Learning 76: 211-225, Springer
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-09)
Bled, Slovenia, September 2009 Machine Learning Journal Best Student Paper Award

Weiwei Cheng, Jens Hühn, Eyke Hüllermeier
Decision tree and instance-based learning for label ranking [pdf][bibtex][slides][poster][video]
Proceedings of the 26th International Conference on Machine Learning (ICML-09): 161-168, Omnipress
Montreal, Canada, June 2009 ICML scholarship

Weiwei Cheng, Eyke Hüllermeier
A new instance-based label ranking approach using the Mallows model [pdf][bibtex][slides]
LNCS 5551 Advances in Neural Networks: 707-716, Springer
The 6th International Symposium on Neural Networks (ISNN-09)
Wuhan, China, May 2009

Weiwei Cheng, Eyke Hüllermeier
Ranking skylines using active learning techniques [pdf][bibtex]
Proceedings of Chinese Intelligent Systems Engineering 2008 (CNISE-08)
Chengdu, China, October 2008

Weiwei Cheng, Eyke Hüllermeier
Instance-based label ranking using the Mallows model [pdf][bibtex]
Workshop Proceedings of Preference Learning 2008 (PL-08)
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD-08)
Antwerp, Belgium, September 2008

Weiwei Cheng, Eyke Hüllermeier
Instance-based label ranking using the Mallows model
Workshop Proceedings of ECCBR-08: 143-157
Uncertainty and Knowledge Discovery in CBR
The 9th European Conference on Case-Based Reasoning (ECCBR-08)
Trier, Germany, September 2008

Weiwei Cheng, Eyke Hüllermeier
Learning similarity functions from qualitative feedback [pdf][bibtex][slides]
LNAI 5239 Advances in Case-Based Reasoning: 120-134, Springer
The 9th European Conference on Case-Based Reasoning (ECCBR-08)
Trier, Germany, September 2008 nominated for best paper award

Eyke Hüllermeier, Johannes Fürnkranz, Weiwei Cheng, Klaus Brinker
Label ranking by learning pairwise preferences [pdf][bibtex]
Artificial Intelligence 172: 1897-1916, Elsevier Artificial Intelligence Journal Prominent Paper Award 2015

Weiwei Cheng
Interactive ranking of skylines using machine learning techniques
Master's thesis
Faculty of Computer Science, Otto von Guericke University Magdeburg
Magdeburg, Germany, October 2007

Weiwei Cheng, Eyke Hüllermeier, Bernhard Seeger, Ilya Vladimirskiy
Interactive ranking of skylines using machine learning techniques [pdf][bibtex][poster]
Proceedings of Lernen-Wissen-Adaptivität 2007 (LWA-07): 141-148, Martin Luther University Halle-Wittenberg
Halle, Germany, September 2007
my page on Google Scholar Citations


Patents

Valentin Flunkert, Weiwei Cheng, inventors; Amazon Technologies, Inc., assignee
Artificial intelligence system using deep neural networks for pairwise character-level text analysis and recommendations
US patent application, November 2017

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Artificial intelligence system for generating network-accessible recommendations with explanatory metadata
US patent application, September 2017

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Determining representative items using a diversity scoring strategy
US patent application, November 2016

Weiwei Cheng, Christopher Gonzales, inventors; Amazon Technologies, Inc., assignee
Document content analysis based on topic modeling (user interfaces)
US patent application, September 2016

Weiwei Cheng, Christopher Gonzales, inventors; Amazon Technologies, Inc., assignee
Document content analysis based on topic modeling
US patent application, September 2016

Weiwei Cheng, Amanda Dee Bottorff, Sandeep Ranganathan, inventors; Amazon Technologies, Inc., assignee
Extracting keywords from a document
US patent application, September 2016

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Generating a set of representative items using a dynamic selection strategy
US patent application, April 2016

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Generating a set of representative items using a clustering selection strategy
US patent application, April 2016

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Generating a set of representative items using a maximum-set-coverage selection strategy
US patent application, April 2016

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Generating a set of diversified items
US patent application, December 2015

Weiwei Cheng, inventor; Amazon Technologies, Inc., assignee
Machine learning based analysis of reviews
US patent application, December 2014


Talks & Tutorials

Salience rank: efficient keyphrase extraction with topic modeling [slides]
Data Science Luxembourg
Luxembourg City, Luxembourg, September 2017

Applying natural language processing at Amazon
Amazon-Oxford-Warwick Workshop on Machine Learning Applications and Computational Statistics
Berlin, Germany, May 2016

Preference learning using statistical methods for label ranking [slides]
Seminars on Machine Learning at Poznan University of Technology
Poznan, Poland, March 2014

Preference-based evolutionary direct policy search [pdf][slides]
Dagstuhl Seminar 13321: The 11th European Workshop on Reinforcement Learning (EWRL-13)
Dagstuhl, Germany, August 2013

Preference-based reinforcement learning [slides]
The 25th European Conference on Operational Research (EURO-12)
Vilnius, Lithuania, July 2012 DAAD conference scholarship

Learning monotone nonlinear models using the Choquet integral [slides][video]
Lernen-Wissen-Adaptivität (LWA-11)
Magdeburg, Germany, September 2011

The RipOff! game: a tutorial of cooperative game theory [slides]
with Yoram Bachrach
Think Computer Science 2010
Cambridge, UK, December 2010

Graded multi-label classification: the ordinal case [slides]
Lernen-Wissen-Adaptivität (LWA-10)
Kassel, Germany, September 2010

Acceptance speech of 2009 Chinese Government Award for Outstanding Self-Financed Students Abroad [pdf-zh][pdf-en]
Embassy of China
Berlin, Germany, June 2010

Text Classification: concepts and methods [pdf][slides]
Association of Chinese Computer Scientists in Germany (GCI) 2009 Annual Conference
Fürth, Germany, November 2009

Text Classification: a back-to-school tutorial
GTO IES Audit & Risk Management Department, Deutsche Bank
Frankfurt, Germany, November 2009

Human vs computer: case studies [slides]
Association of Chinese Scholars and Students in Magdeburg (VCWSM e.V.)
Magdeburg, Germany, October 2009

Multi-label classification: a new machine learning problem [slides][video]
Lightning Talk, the 4th Annual Google Test Automation Conference (GTAC-09)
Zurich, Switzerland, October 2009

Combining instance-based learning and logistic regression for multi-label classification [slides][video]
Lernen-Wissen-Adaptivität (LWA-09)
Darmstadt, Germany, September 2009

Human-computation in internet [pdf][slides]
Association of Chinese Computer Scientists in Germany (GCI) IT Strategy Workshop
Schwetzingen, Germany, September 2009

Ranking the skyline: an application of preference learning [proceedings][slides]
Association of Chinese Computer Scientists in Germany (GCI) 2008 Annual Conference
Lahnstein, Germany, November 2008

Instance based label ranking [slides]
Student Talk, the 10th Machine Learning Summer School (MLSS-08)
Ile De Re, France, September 2008 MLSS scholarship

A brief introduction to preference handling [slides]
Colloquium for graduate students in Mathematics and Computer Science at Philipps University Marburg
Marburg, Germany, March 2007


Honors & Awards

Prominent paper award [pic 1 2]
Artificial Intelligence Journal Prominent Paper Award 2015
The 24th International Joint Conference on Artificial Intelligence
Buenos Aires, Argentina, July 2015

Best paper award [pic]
The 21st International Conference on Case-Based Reasoning
Saratoga Springs, USA, July 2013

DAAD conference scholarship
German Academic Exchange Service (DAAD)
Vilnius, Lithuania, July 2012

Data mining competition award [pic]
The 2nd place at JRS 2012 Data Mining Competition
Chengdu, China, April 2012

NIPS travel grant
Sponsored by Winton Capital, etc.
The 25th Annual Conference on Neural Information Processing Systems
Granada, Spain, December 2011

DAAD STIBET scholarship
Sponsored by German Academic Exchange Service (DAAD)
Marburg University Research Academy
Marburg, Germany, April 2011

Nomination for best student paper award [pic]
The 7th Conference of the European Society for Fuzzy Logic and Technology
Aix-les-Bains, France, July 2011

UNESCO ECMLPKDD conference grant
Sponsored by UNESCO Chair in Data Privacy
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Barcelona, Spain, September 2010

ICML scholarship [link]
Sponsored by IBM, National Science Foundation (NSF), etc.
The 27th International Conference on Machine Learning
Haifa, Israel, June 2010

Outstanding Chinese student award [pic][link de1 de2 zh1 zh2 zh3][video CCTV CRIOnline]
Chinese Government Award for Outstanding Self-Financed Students Abroad
Ministry of Education of the People's Republic of China
Berlin, Germany, June 2010

Best paper award [pic][video]
Machine Learning Journal Best Student Paper Award
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Bled, Slovenia, September 2009

ICML scholarship [link]
Sponsored by National Science Foundation (NSF), etc.
The 26th International Conference on Machine Learning
Montreal Canada, June 2009

Best graduate award [pic]
Best graduate 2007/2008 in Master of Data and Knowledge Engineering
Otto von Guericke University Magdeburg
Magdeburg, Germany, October 2008

MLSS scholarship
Sponsored by Predict & Control and Lille's Computer Science Laboratory
The 10th Machine Learning Summer School
Ile De Re, France, September 2008

Nomination for best paper award
The 9th European Conference on Case-Based Reasoning
Trier, Germany, September 2008

Outstanding international student scholarship [pdf]
Ministry of Education and Cultural Affairs of Saxony-Anhalt
Magdeburg, Germany, October 2006

Best debater award [pic]
The 1st Henan Varsity Debate Tournament
Zhengzhou, China, April 2003

Speech contest award [pic]
The 3rd prize in Speech Contest “The 50 Years”
Anqing, China, August 1999


Some Links

Blog
http://chengweiwei.wordpress.com/
Photos
https://get.google.com/albumarchive/108838342818898730913
Twitter