Zesheng Ye

I am a PhD candidate at Data Dynamics group, School of Computer Science and Engineering, the University of New South Wales (UNSW) since Sep 2020. I am fortunate to be advised by Prof. Lina Yao. Prior to this, my master and undergraduate studies were at UNSW and Southwest Jiaotong University, respectively.

My primary research interests revolve around enabling uncertainty-awareness, identifiability, and transferability in real-world machine learning deployment, particularly in addressing challenges like distribution shift and sample efficiency. I also have broad interests in perception, understanding and decision-making tasks under multi-modal and resource limited human-centric environments. To date, our empirical studies has covered sensor-based human physiological recognition (Brain-Computer Interface, Activity Recognition), cold-start Recommender Systems, and Motion Forecasting.

Works

Publications

• Jing Du*, Zesheng Ye*, Bin Guo, Zhiwen Yu, and Lina Yao. "Distributional Domain-Invariant Preference Matching for Cross-Domain Recommendation". IEEE International Conference on Data Mining [C] (ICDM2023).
• Zesheng Ye, Jing Du, Yao Liu, Yihong Zhang, Lina Yao. "NP-SSL: A Modular and Extensible Self-supervised Learning Library with Neural Processes". The 32nd ACM International Conference on Information and Knowledge Management [C] (CIKM2023).
• Zesheng Ye, Lina Yao, Yu Zhang, Sylvia Gustin. "See What You See: Self-supervised Cross-Modal Visual Retrieval from Brain Activity". Pattern Recognition [J] (PR).
• Haowei Lou, Zesheng Ye, Yu Zhang, Lina Yao. "Less is More: Brain Functional Connectivity Empowered Generalisable Intention Classification with Task-relevant Channel Selection". IEEE Transactions on Neural Systems and Rehabilitation Engineering [J] (TNSRE).
• Jing Du, Zesheng Ye, Bin Guo, Zhiwen Yu, and Lina Yao. "Interest Dynamics Modeling using Generative Neural Processes". The 16th ACM International Conference on Web Search and Data Mining [C] (WSDM2023).
• Jing Du, Zesheng Ye, Lina Yao, Bin Guo and Zhiwen Yu. "Socially-aware Dual Contrastive Learning for Cold-Start Recommendation". The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval [C] (SIGIR2022).
• Zesheng Ye, and Lina Yao. "Contrastive Conditional Neural Processes". 2022 Conference on Computer Vision and Pattern Recognition [C] (CVPR2022).
• Kaixuan Chen, Dalin Zhang, Zesheng Ye, Lina Yao. "Deep Multi-Agent Attentional Learning for Cognitive Attention Analysis in Educational Context". The 28th International Joint Conference on Artificial Intelligence (IJCAI2019) workshop on AIMA4EDU (Best Student Paper Award).

Working papers

• Zesheng Ye, Jing Du, Yao Liu, Yihong Zhang, Lina Yao. "Uncertainty-Aware Test-Time Adaptation for Subject-Independent Human-Centric Physiological Time-series Recognition". [under review].
• Jing Du*, Zesheng Ye*, Bin Guo, Zhiwen Yu, and Lina Yao. " Identifiability of Cross-Domain Recommendation via Causal Subspace Disentanglement". [under review].
• Yao Liu*, Zesheng Ye*, Binghao Li, Lina Yao. "Uncertainty-Aware Pedestrian Trajectory Prediction via Distributional Diffusion". On Preprint.
• Zesheng Ye, Jing Du, Lina Yao. "Adversarially Contrastive Estimation of Conditional Neural Processes". On Preprint.
• Haodong Lu, Zesheng Ye, Lina Yao. "Adaptive Dynamic Pooling for Weakly-Supervised Temporal Action Localisation". [under review]

Experience

• RA, School of Computer Science, University of Technology (UTS), Aug 2019 - Dec 2019
• Hosted by Dr. Xianzhi Wang
• Work on algorithms regarding few-shot learning and domain adaptation

Services

PC member & Reviewer & Sub-reviewer

• Journals
• [2023]. ACM Transactions on Intelligent Systems and Technology (TIST)
• [2022]. ACM Trans. Asian and Low-Resource Language Information Processing (TALLIP)
• [2021]. Trans. Neural Networks and Learning Systems (TNNLS), Scientific Report, Knowledge-Based Systems (KBS)
• [2020]. ACM Transactions on Sensor Networks (TOSN)
• [2019]. Information Sciences Journal
• Conferences
• [2024]. CVPR-24, TheWebConf-24
• [2023]. ADMA-23, CVPR-23, WWW-23
• [2022]. AAAI-22, CVPR-22, KDD-22, SIGIR-22, DASFAA-2022, ADMA-22, PAKDD-22
• [2021]. ICML-21, IJCAI-21, PAKDD-21, KDD-21, ICCV-21, ACM MM-21, CIKM-21, ACML-21
• [2020]. ACM MM-20, PKADD-20, IPSN-20
• [2019]. ICONIP-19, Australasian Joint Conference on Artificial Intelligence-19

Teaching

Research Supervision

• Zilu Dong, Honours research project (UNSW), Brain Signal Visualization, Feb 2021 - Nov 2021, co-supervised with Prof. Lina Yao
• Yi Su, Master research project (UNSW), Multimodal Human Activity Recognition, May 2021 - Nov 2021, co-supervised with Prof. Lina Yao
• Haodong Lu, Honours research project (UNSW), Weakly-supervised Temporal Activity Detection, Jun 2021 - Jun 2022, co-supervised with Prof. Lina Yao
• Haowei Lou, Master by Research (UNSW), Lightweight Machine Learning with Brain Signals, Mar 2022 - Jul 2023, co-supervised with Prof. Lina Yao

Casual Academic

• TA, COMP9727 Recommender Systems, 22T2, UNSW
• TA, COMP9417 Machine Learning and Data Mining, 19T2, UNSW
• TA, MARK5828 Advertisement Analytics, 19T1, UNSW

Awards

• UNSW University International Postgraduate Award (UIPA) 2020-2023
• UNSW Tuition Fee Scholarship 2020-2024
• ARC Grant Funded Computer Science Scholarship 2020-2024
• UNSW Graduate with Excellence 2019
• UNSW CSE Performance Award

Can be reached at zesheng[dot]ye [at] unsw[dot]edu[dot]au