Ziwei Zhu

Ziwei Zhu (竺子崴)

About Me

Howdy! I am a fifth-year Ph.D. candidate in the Computer Science & Engineering Department at Texas A&M University, advised by Prof. James Caverlee. I obtained my Bachelor's degree in Computer Science from Wuhan University in China before coming to TAMU.

I am broadly interested in data mining, machine learning, and information retrieval, with a special emphasis on augmenting responsibility in AI-powered user-centered systems to provide fair, unbiased, accountable, and trustworthy information services for both end users and society-at-large. Specifically, my Ph.D. dissertation research focuses on one of the most important types of user-centered systems -- the personalized recommender system, and aims to lay the foundation for new responsible recommender systems by identifying, analyzing, and addressing unfairness and bias issues in machine learning based recommendation algorithms and systems.

News

  • 01/2022: A paper about fairness in learning-to-rank is accepted to WWW 2022 Web4Good track.
  • 11/2021: Invited to be a PC member for KDD 2022 Applied Science Track.
  • 10/2021: A long paper about user mainstream bias in recommendation is accepted to WSDM 2022.
  • 08/2021: Gave an oral presentation for our accepted paper at KDD 2021.
  • 07/2021: Gave an oral presentation for our accepted paper at SIGIR 2021.
  • 07/2021: Gave a talk about recommendation fairness among cold-start items at Netflix research seminar.
  • 06/2021: Invited to be a PC member for WSDM 2022.
  • 05/2021: A long paper about popularity bias in dynamic recommendation is accepted to KDD 2021.
  • 04/2021: Gave a talk about fairness in recommender systems at University of North Texas.
  • 04/2021: A long paper about recommendation fairness among cold-start items is accepted to SIGIR 2021.

Publications

(Google Scholar) (Semantic Scholar)

2022

  • [WWW Web4Good 2022] End-to-end Learning for Fair Ranking Systems.
    The Web4Good special track in 33rd ACM International Conference on World Wide Web, 2022.
    James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck, and Ziwei Zhu.

  • [WSDM 2022] Fighting Mainstream Bias in Recommender Systems via Local Fine Tuning. [pdf] [code]
    The 15th ACM International Conference on Web Search and Data Mining, 2022.
    Ziwei Zhu and James Caverlee.

2021

  • [KDD 2021] Popularity Bias in Dynamic Recommendation. [pdf] [code] [slides] [poster]
    The 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2021.
    Ziwei Zhu, Yun He, Xing Zhao, and James Caverlee.

  • [SIGIR 2021] Fairness among New Items in Cold Start Recommender Systems. [pdf] [code] [slides]
    The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021.
    Ziwei Zhu, Jingu Kim, Trung Nguyen, Aish Fenton, and James Caverlee.

  • [WWW 2021] Rabbit Holes and Taste Distortion: Distribution-Aware Recommendation with Evolving Interests. [pdf]
    The 32nd International Conference on World Wide Web, 2021.
    Xing Zhao, Ziwei Zhu, and James Caverlee.

  • [SDM 2021] Session-based Recommendation with Hypergraph Attention Networks. [pdf]
    The 2021 SIAM International Conference on Data Mining, 2021.
    Jianling Wang, Kaize Ding, Ziwei Zhu, and James Caverlee.

  • [WSDM 2021] Popularity-Opportunity Bias in Collaborative Filtering. [pdf] [slides] [poster]
    The 14th ACM International Conference on Web Search and Data Mining, 2021.
    Ziwei Zhu, Yun He, Xing Zhao, Yin Zhang, Jianling Wang, and James Caverlee.

2020

  • [EMNLP 2020] Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition. [pdf] [code]
    The 2020 Conference on Empirical Methods in Natural Language Processing.
    Yun He, Ziwei Zhu, Yin Zhang, Qin Chen, and James Caverlee.

  • [RecSys 2020] Unbiased Implicit Recommendation and Propensity Estimation via Combinational Joint Learning. (short paper) [pdf] [code] [poster]
    The 14th ACM Conference on Recommender Systems, 2020.
    Ziwei Zhu, Yun He, Yin Zhang, and James Caverlee.

  • [RecSys 2020] Content-Collaborative Disentanglement Representation Learning for Enhanced Recommendation. [pdf] [slides]
    The 14th ACM Conference on Recommender Systems, 2020.
    Yin Zhang, Ziwei Zhu, Yun He, and James Caverlee.

  • [SIGIR 2020] Measuring and Mitigating Item Under-Recommendation Bias in Personalized Ranking Systems. [pdf] [code] [SIGIR slides] [extended slides] [arxiv version]
    The 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020.
    Ziwei Zhu, Jianling Wang and James Caverlee.

  • [SIGIR 2020] Recommendation for New Users and New Items via Randomized Training and Mixture-of-Experts Transformation. [pdf] [code] [slides]
    The 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020.
    Ziwei Zhu, Shahin Sefati, Parsa Saadatpanah and James Caverlee.

  • [WWW 2020] Addressing the Target Customer Distortion Problem in Recommender Systems. (short paper) [pdf]
    The 31st International Conference on World Wide Web, 2020.
    Xing Zhao, Ziwei Zhu, Majid Alfifi and James Caverlee.

  • [WSDM 2020] Improving the Estimation of Tail Ratings in Recommender System with Multi-Latent Representations. [pdf]
    The 13th ACM International Conference on Web Search and Data Mining, 2020.
    Xing Zhao, Ziwei Zhu, Yin Zhang and James Caverlee.

  • [WSDM 2020] User Recommendation in Content Curation Platforms. [pdf] [code] [slides]
    The 13th ACM International Conference on Web Search and Data Mining, 2020.
    Jianling Wang, Ziwei Zhu and James Caverlee.

  • [WSDM 2020] Key Opinion Leaders in Recommendation Systems: Opinion Elicitation and Diffusion. [pdf] [poster]
    The 13th ACM International Conference on Web Search and Data Mining, 2020.
    Jianling Wang, Kaize Ding, Ziwei Zhu, Yin Zhang and James Caverlee.

2019

  • [WWW 2019] Improving Top-K Recommendation via Joint Collaborative Autoencoders. (short paper) [pdf] [code] [poster]
    The 30th International Conference on World Wide Web, 2019.
    Ziwei Zhu, Jianling Wang, and James Caverlee.

2018

  • [CIKM 2018] Fairness-Aware Tensor-Based Recommendation. [pdf] [slides] [code]
    The 27th ACM International Conference on Information and Knowledge Management, 2018.
    Ziwei Zhu, Xia Hu, and James Caverlee.

  • [FATREC 2018] Fairness-Aware Recommendation of Information Curators. [pdf]
    The 2nd FATREC Workshop on Responsible Recommendation at RecSys, 2018.
    Ziwei Zhu, Jianling Wang, Yin Zhang, and James Caverlee.

  • [ICDM 2018] Pseudo-Implicit Feedback for Alleviating Data Sparsity in Top-K Recommendation. (short paper) [pdf] [code]
    The 2018 IEEE International Conference on Data Mining, 2018.
    Yun He, Haochen Chen, Ziwei Zhu, and James Caverlee.

2017

  • [BSN 2017] Modeling and Detecting Student Attention and Interest Level Using Wearable Computers. [pdf]
    IEEE International Conference on Wearable and Implantable Body Sensor Networks, 2017.
    Ziwei Zhu, Sebastian Ober, Roozbeh Jafari.

Teaching

  • Guest lecturer: CSCE 489, Special Topics in Recommender Systems, TAMU, Spring 2021
  • Teaching assistant: CSCE 489, Special Topics in Recommender Systems, TAMU, Spring 2021
  • Teaching assistant: CSCE 676, Data Mining and Analysis, TAMU, Fall 2019
  • Teaching assistant: CSCE 206, Structured programming in C, TAMU, Fall 2017

Experience

  • 09/2017 - present: Research assistant at Info Lab, Texas A&M University (advisor: Prof. James Caverlee)
  • 05/2020 - 08/2020: Research intern at Netflix (mentors: Dr. Jingu Kim, Dr. Trung Nguyen, and Aish Fenton)
  • 05/2019 - 08/2019: Research intern at Comcast Applied AI Lab (mentor: Dr. Shahin Sefati)
  • 09/2016 - 08/2017: Research assistant at ESP Lab, Texas A&M University (advisor: Prof. Roozbeh Jafari)

Service

  • Conference program committees: WSDM 2022, KDD 2022
  • Conference External reviewers: WWW 2022, WWW 2021, SIGIR 2021, RecSys 2021, SIGIR 2020, WWW 2019, SIGIR 2019, WWW 2018
  • Journal reviewers: IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Services Computing, IEEE Intelligent Systems, Information Retrieval Journal, ACM Transactions on Information Systems, Information Processing and Management, Big Data Journal, Knowledge-based Systems, Machine Learning Journal

Presentations

     Invited Talks

  • Fairness among New Items in Cold Start Recommender Systems, research seminar at Netflix, 07/2021
  • Toward Fairness-aware Recommender Systems, University of North Texas, 04/2021
  • Item Fairness in Recommender Systems, research seminar at Netflix, 08/2020

     Conference Oral Presentations

  • Popularity Bias in Dynamic Recommendation, KDD 2021, 08/2021
  • Fairness among New Items in Cold Start Recommender Systems, SIGIR 2021, 07/2021
  • Popularity-Opportunity Bias in Collaborative Filtering, WSDM 2021, 03/2020
  • Recommendation for New Users and New Items, SIGIR 2020, 07/2020
  • Measuring and Mitigating Under-Recommendation Bias in Personalized Ranking, SIGIR 2020, 07/2020
  • Fairness-Aware Tensor-Based Recommendation, CIKM 2018, 10/2018

     Conference Poster Presentations

  • Unbiased Implicit Recommendation via Combinational Joint Learning, RecSys 2020, 09/2020
  • Improving Top-K Recommendation via Joint Collaborative Autoencoders, WWW 2019, 05/2019

Awards

  • TAMU CSE Student Travel Award, 2022
  • WSDM Travel Grant, 2022
  • SIGIR Travel Grant, 2021
  • WSDM Travel Grant, 2021
  • SIGIR Travel Grant, 2020
  • CIKM Travel Grant, 2018
  • First Class Scholarship at Wuhan University (top 5% students), 2015
  • National Scholarship, Wuhan University (top 1% students), 2014
  • Third Class Scholarship at Wuhan University (top 30% students), 2013