Xinyan Dai

---

I am a Ph.D candidate at The Chinese University of Hong Kong, under the supervision of James Cheng. Before coming to CUHK, I got my bachelor degree from Nanjing University in 2018.

My research mainly focuses on Similarity Search and Machine Learning. Typically, I am interested in applying similarity search techniques (Locality Sensitive Hashing, Sketching, Vector Quantization) on large scale machine learning.

Email: xinyan (dot) dai [at] outlook (dot) com

Publications

---

under review

• Xinyan Dai, Xiao Yan, Kaiwen Zhou, Han Yang, Kelvin K. W. Ng, James Cheng, Fan Yu.
  Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning. [arxiv] [github]
  

2020

• Xinyan Dai, Xiao Yan, Kaiwen Zhou, Yuxuan Wang, Han Yang, James Cheng.
  Convolutional Embedding for Edit Distance. [arxiv] [github]
  In 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), Xi'anVirtual Event, China, 2020.

• Xinyan Dai*, Xiao Yan*, Kelvin K. W. Ng, Jie Liu, James Cheng.
  Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product Search. [arxiv] [github]
  In AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 2020, Oral.

• Jie Liu*, Xiao Yan*, Xinyan Dai, James Cheng, Ming-Chang Yang.
  Understanding and Improving Proximity Graph based Maximum Inner Product Search. [arxiv] [github]
  In AAAI Conference on Artificial Intelligence (AAAI), New York, USA, 2020.

• Yitong Meng, Xinyan Dai, Xiao Yan, James Cheng, Weiwen Liu, Jun Guo, Benben Liao, Guangyong Chen.
  PMD: A Novel User Distance for Recommender Systems. [link] [github]
  In European Conference on Information Retrieval (ECIR), Lisbon, Portugal, 2020, short paper.

2018

• Xiao Yan, Jinfeng Li, Xinyan Dai, Hongzhi Chen, and James Cheng.
  Norm-Ranging LSH for Maximum Inner Product Search. [arxiv] [github]
  In Advances in Neural Information Processing Systems (NeurIPS), Montréal Canada, 2018.

Service

---

• External Reviewer of International Conference on Very Large Data Bases (VLDB), 2019
• External Reviewer of SIGMOD International Conference on Management of Data, 2019

Teaching Assistant

---

• Introduction to Computing Using C++ (CSCI1120), 2020-2021 Term 1
• Engineering Practicum (AIST2602), 2019-2020 Term 2, 2020-2021 Term 2
• Problem Solving By Programming (ENGG1110), 2018-2019 Term 1 & 2, 2019-2020 Term 1

unique visitors since May 2019

---

Last updated: May the 4th, 2020.