Zhen Wang

I am currently a researcher working for DAMO Academy. During the years of my Ph.D. (as an intern at MSRA), I have pursued the goal of embedding everything (entity, word, sentence, paragraph, etc.). In my experience as an engineer for Alibaba Cloud, I have been lucky to work with people from RISELab who kindly acknowledge my contributions and let me become a committer of Ray. I have a broad interest in machine learning. At the moment, our team is focused on federated learning and working on platforms, benchmarks, and research problems that are related to it.

Education

Sun Yat-sen University, Guangzhou, Guangdong, China

  • Ph.D., Computer Applied Technology, Sep 2012 - Jun 2017
  • B.E., Software Engineering, Sep 2008 - Jun 2012

Research Experience

Microsoft Research Asia (MSRA), Beijing, China

  • Research Intern, Data Mining and Enterprise Intelligence Group, Mentor: Dr. Jun Yan and Dr. Wei-Ying Ma, Feb 2016 – Apr 2017
    • Data-driven metaphor learning (demo)
  • Research Intern, Machine Learning Group, Mentor: Dr. Jianwen Zhang and Dr. Zheng Chen, Oct 2013 – Jan 2016
    • Fact-based Q&A (demo)
    • Heterogenous data embedding (product)
  • Research Intern, Web Search and Mining Group, Mentor: Dr. Zhongyuan Wang and Dr. Haixun Wang, Oct 2011 – Jun 2012
    • Fact extraction from Web tables (demo)
    • Short text representation (product)

Alibaba group and Tsinghua University joint post-doc, Advisor: Dr. Jingren Zhou and Dr. Minlie Huang, Nov 2018 - present

  • Reinforcement learning in E-commerce scenarios (ongoing)

Publications (google scholar)

  • Jinjia Feng, Zhen Wang, Yaliang Li, Bolin Ding, Zhewei Wei, Hongteng Xu. MGMAE: Molecular Representation Learning by Reconstructing Heterogeneous Graphs with A High Mask Ratio. CIKM 2022 Full Paper.
  • Yaliang Li, Bolin Ding, Zhen Wang, Yuexiang Xie, Dawei Gao, Liuyi Yao, Daoyuan Chen, Weirui Kuang, Hongzhu Shi, Jingren Zhou. A Practical Introduction to Federated Learning. KDD 2022 Tutorial (website)
  • Zhen Wang, Weirui Kuang, Yuexiang Xie, Liuyi Yao, Yaliang Li, Bolin Ding, Jingren Zhou. FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning. KDD 2022 Full Paper.
  • Zhen Wang, Yaliang Li, Zhewei Wei, Weirui Kuang, Bolin Ding. Graph Neural Networks with Node-wise Architecture. KDD 2022 Full Paper.
  • Dawei Gao, Yuexiang Xie, Zimu Zhou, Zhen Wang, Yaliang Li, Bolin Ding. Finding Meta Winning Ticket to Train Your MAML., KDD 2022 Full Paper.
  • Yuexiang Xie, Zhen Wang, Yaliang Li, Ce Zhang, Jingren Zhou, Bolin Ding. iFlood: A Stable and Effective Regularizer. ICLR 2022 Full Paper.
  • Shaoyun Shi, Yuexiang Xie, Zhen Wang, Bolin Ding, Yaliang Li, Min Zhang. Explainable Neural Rule Learning. WWW 2022 Full Paper.
  • Yiqing Xie, Zhen Wang, Carl Yang, Yaliang Li, Bolin Ding, Hongbo Deng, Jiawei Han. KoMen: Domain Knowledge Guided Interaction Recommendation for Emerging Scenarios. WWW 2022 Full Paper.
  • Yaliang Li, Zhen Wang, Yuexiang Xie, Bolin Ding, Ce Zhang, Kai Zeng, Rong Zhu. AutoML: From Methodology to Application. CIKM 2021 Tutorial (website).
  • Yaliang Li, Zhen Wang, Yuexiang Xie, Bolin Ding, Ce Zhang. AutoML: A Perspective where Industry Meets Academy. KDD 2021 Tutorial (website).
  • Yuexiang Xie*, Zhen Wang*, Yaliang, Li, Bolin Ding, Nezihe Merve Gürel, Ce Zhang, Minlie Huang, Wei Lin, Jingren Zhou. FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data. KDD 2021 Full Paper.
  • Zhao Li, Junshuai Song, Zehong Hu, Zhen Wang, Jun Gao. Constrained Dual-level Bandit for Personalized Impression Regulation in Online Ranking Systems., TKDD 2021.
  • Daoyuan Chen, Yaliang Li, Minghui Qiu, Zhen Wang, Bofang Li, Bolin Ding, Hongbo Deng, Jun Huang, Wei Lin, and Jingren Zhou. AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search. IJCAI 2020 Full Paper.
  • Fei Xiao, Zhen Wang, Haikuan Huang, Jun Huang, Xi Chen, Hongbo Deng, Minghui Qiu. AliISA: Creating an Interactive Search Experience in E-commerce Platforms. SIGIR 2019 Demo.
  • Zehong Hu, Zhen Wang, Zhao Li, Shichang Hu, Shasha Ruan, Jie Zhang. Fraud Regulating Policy for E-Commerce via Constrained Contextual Bandits. AAMAS 2019 Full Paper.
  • Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang. Chapter 5 of Artificial Intelligence for Prosthetics-challenge solutions. NurIPS 2018 RL Challenge Tech Report.
  • Huaping Zhong, Jianwen Zhang, Zhen Wang, Hai Wan, Zheng Chen. Aligning Knowledge and Text Embeddings by Entity Descriptions. EMNLP 2015 Short Paper.
  • Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen. Knowledge Graph and Text Jointly Embedding. EMNLP 2014 Full Paper.
  • Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen. Knowledge Graph Embedding by Translating on Hyperplanes. AAAI 2014 Full Paper.

(*Equal contribution.)

Awards & Scholarships

  • KDD Cup, AutoML Track, 4/149, May 2020 (our solution)
  • NeurIPS RL Challenge 5/427, Nov 2018 (our solution)
  • National Scholarship, Sep 2014
  • Silver Medal in ACM/ICPC Asia Regional Contest, Oct 2011
  • National Scholarship, Sep 2009

Working Experience

Alibaba Group, Hangzhou, Zhejiang, China

  • Algorithm Expert (P7), Data Analytics and Intelligence Lab, June 2020 - present

    • FederatedScope: a federated learning platform with an event-driven programming paradigm.
    • FederatedScope-GNN: a federated graph learning package.
    • FedHPO-B: a federated HPO benchmark suite.
  • Algorithm Expert (P7), Deep Learning Algorithm Division, July 2019 - May 2020

    • Neural architecture search utilities: DARTS, ASAP, ProxylessNAS, etc.
    • Auto feature engineering utilities: AutoCross and some RL-based search strategies
    • EasyRL: TensorFlow-based RL package
  • Senior Algorithm Engineer (P6), Large Scale Learning-Innovative Algorithm Division, July 2017 - June 2019

    • Double 11 bundle recommendation business: a model for CTR prediction
    • A3gent: an internal deep reinforcement learning package
    • Ray: I contribute the implementations of several RL algorithms, e.g., DDPG, Rainbow, and MARWIL, to Ray RLLib and become a committer
    • Fraud regularization and flow control: constrained contextual bandit
    • Interactive shopping assistant: hierarchical reinforcement learning

Skills

  • Programming languages: Python
  • Machine leanring libraries: TensorFlow, PyTorch
  • Foreign language: English (CET-6 certification)