DRL4IR: The 3rd Workshop on Deep Reinforcement Learning for Information Retrieval at SIGIR'22

9:00-12:00AM, July 15, 2022 (CET time)

Onsite: Floor -1, Círculo de Bellas Artes, Madrid

Online: Zoom Link

Backup Zoom Link

INTRO

Information retrieval (IR) techniques, such as search, recommendation and online advertising, satisfying users’ information needs by suggesting users personalized objects (information or services) at the appropriate time and place, play a crucial role in mitigating the information overload problem. Since the widely use of mobile applications, more and more information retrieval services have provided interactive functionality and products. Thus, learning from interaction becomes a crucial machine learning paradigm for interactive IR, which is based on reinforcement learning. With recent great advances in deep reinforcement learning (DRL), there have been increasing interests in developing DRL based information retrieval techniques, which could continuously update the information retrieval strategies according to users’ real-time feedback, and optimize the expected cumulative long-term satisfaction from users.

Our workshop is a full-day workshop DRL4IR at SIGIR 2022, with the aim to provide a venue, which can bring together academia researchers and industry practitioners (i) to discuss the principles, limitations and applications of DRL for information retrieval, and (ii) to foster research on innovative algorithms, novel techniques, and new applications of DRL to information retrieval.

Our 2nd DRL4IR workshop at SIGIR 2021 [Website].

PROGRAM

Zoom Link

9:00am-12:00am, CET Time      15:00pm-18:00pm, Beijing Time

0:00am-3:00am, LA time      3:00am-6:00am, New York Time

  • [Openning (9:00 - 9:10)]
  • Grace Hui Yang (Goergetown University)
  • [Keynote 1 (9:10 - 9:50)] Multi-objective Reinforcement Learning for Recommender Systems
  • Alexandros Karatzoglou (Staff Research Scientist, Google)
  • [Invited Talk 1 (9:50 - 10:20)] Reinforcement Learning for Industrial Recommender Systems
  • Qingpeng Cai (Staff Algorithm Engineer, KuaiShou)
  • [Paper Talk 1 (10:20 - 10:30)] BCRLSP: an offline reinforcement learning framework for sequential targeted promotion
  • Fanglin Chen, Xiao Liu, Bo Tang, Feiyu Xiong, Serim Hwang and Guomian Zhuang (NYU, CMU and Alibaba)
  • Coffee Break (10:30 - 11:00)
  • [Keynote 2 (11:00 - 11:40)] Learning to Rank and Reinforcement Learning: Surprising Connections and Important Differences
  • Harrie Oosterhuis (Assistant Professor at Radboud University Nijmegen, and Staff Machine Learning Scientist at Twitter)
  • [Invited Talk 2 (11:40 - 12:10)] A Real-World Industrial Benchmark for Deep Reinforcement Learning Based Recommender System (Hands-on)
  • Kai Wang (Senior AI Expert), and Runze Wu (Senior AI Expert & Research Lead, Fuxi AI Lab, NetEase Games)
  • [Paper Talk 2 (12:10 - 12:20)] Balancing Utility and Exposure Fairness for Integrated Ranking with Reinforcement Learning
  • Wei Xia, Weiwen Liu, Yifan Liu and Ruiming Tang (Huawei Noah's Art Lab and SJTU)
  • ORGANIZERS

    Image

    Xiangyu Zhao City University of Hong Kong

    Image

    Xin Xin Shandong University

    Image

    Weinan Zhang Shanghai Jiao Tong University

    Image

    Li Zhao Microsoft Research Asia (MSRA)

    Image

    Dawei Yin Baidu

    Image

    Grace Hui Yang Georgetown University