About Me

I'm a software engineer at Google Research (Brain team). I obtained my Ph.D. from UC San Diego, advised by Prof. Julian McAuley. I'm interested in recommender systems, deep learning. Previously, I was fortunate to work with Prof. Wu-Jun Li and Prof. Zhi-Hua Zhou at LAMDA Group of Nanjing University. I did some work of learning binary representation (called learning to hash) of images for fast image retrieval.

I spent great summers at Google Brain (Mountain View, 2019), Pinterest Labs (San Francisco, 2018), and Adobe Research (San Jose, 2017) as a research intern.


Publications

Deep Hash Embedding for Large-Vocab Categorical Feature Representations[preprint]

Wang-Cheng Kang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyan Yi, Ting Chen, Lichan Hong, Ed H. Chi

Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems[pdf]

Innovation in Data Science workshop at The Web Conference 2020, IID@WWW'20
Wang-Cheng Kang, Derek Zhiyuan Cheng, Ting Chen, Xinyan Yi, Dong Lin, Lichan Hong, Ed H. Chi

Candidate Generation with Binary Codes for Large-scale Top-N Recommendation[pdf][code]

ACM International Conference on Information and Knowledge Management, CIKM'19
Wang-Cheng Kang, Julian McAuley

CosRec: 2D Convolutional Neural Networks for Sequential Recommendation[pdf][code]

ACM International Conference on Information and Knowledge Management, CIKM'19
An Yan, Shuo Cheng, Wang-Cheng Kang, Mengting Wan, Julian McAuley

Self-Attentive Sequential Recommendation[pdf][preprint][code/data]

IEEE International Conference on Data Mining, ICDM'18 (long paper, acceptance rate 9%)
Wang-Cheng Kang, Julian McAuley

Recommendation through Mixtures of Heterogeneous Item Relationships[pdf][code/data]

ACM International Conference on Information and Knowledge Management, CIKM'18
Wang-Cheng Kang, Mengting Wan, Julian McAuley

Learning Consumer and Producer Embeddings for User-Generated Content Recommendation[pdf][code/data]

ACM Conference on Recommender Systems, RecSys'18
Wang-Cheng Kang, Julian McAuley

Translation-based Recommendation: A Scalable Method for Modeling Sequential Behavior[pdf][code][data]

International Joint Conference on Artificial Intelligence, IJCAI'18 (Sister Conference Best Paper Track, invited paper)
Ruining He, Wang-Cheng Kang, Julian McAuley

Translation-based Recommendation[pdf][code][data]

ACM Conference on Recommender Systems, RecSys'17 (Best Paper Runner-up)
Ruining He, Wang-Cheng Kang, Julian McAuley

Column Sampling based Discrete Supervised Hashing[pdf][code]

AAAI Conference on Artificial Intelligence, AAAI'16
Wang-Cheng Kang, Wu-Jun Li, Zhi-Hua Zhou

Feature Learning based Deep Supervised Hashing with Pairwise Labels[pdf][code]

International Joint Conference on Artificial Intelligence, IJCAI'16 (The 2nd Most Cited Paper, 2/551)
Wu-Jun Li, Sheng Wang, Wang-Cheng Kang

Awards

  • Best Paper Runner-up ACM RecSys, 2017
  • Powell Fellowship UCSD, 2016-2019
  • CCF Outstanding Undergraduate Award CCF, 2015
  • Microsoft Young Fellowship MSRA, 2015
  • The Best Development Award (Champion) of Suning IT Elites of Campus Competition Suning, 2014
  • Gold medal of ACM-ICPC Asia Chengdu Regional Contest ACM, 2013
  • Gold medal of ACM-ICPC Asia Hangzhou Regional Contest ACM, 2013
  • 3rd place of Tencent Hackathon National Finals Tencent, 2013
  • Silver medal of National Olympiad in Informatics CCF 2011

Professional Services

PC Member & Reviewer
  • ICLR'21, AAAI'21, TheWebConf'21, IJCAI'21 (Senior PC)
  • RecSys'20, ICML'20, SDM'20, AAAI'20, CIKM'20, NeurIPS'20, WebSci'20, CogSci'20, ICWSM'20
  • RecSys'19, NeurIPS'19, ICML'19, CogSci'19, ICWSM'19, SDM'19
  • RecSys'18 (Best Reviewer Nominee), Machine Learning Meets Fashion Workshop@KDD'18
Journal Reviewer
  • ACM Computing Surveys (CSUR)
  • IEEE Transactions on Knowledge and Data Engineering (TKDE)
  • The International Journal on Very Large Data Bases (VLDBJ)
  • Transactions on Knowledge Discovery from Data (TKDD)
  • ACM Transactions on the Web (TWEB)
  • IEEE Access
  • PeerJ Computer Science

© 2015 Curriculum Vitae All Rights Reseverd | Design by W3layouts