Rate My Professor Weijia Zhang

Zhang's research focuses on causal inference, machine learning, and survival analysis, particularly bridging gaps between statistical causal inference and weakly supervised machine learning techniques. Key publications include 'Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees' (AAAI 2024), 'Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning' (NeurIPS 2023), 'Multi-instance partial-label learning: Towards exploiting dual inexact supervision' (Science China Information Sciences, 2023), 'Multi-instance causal representation learning for instance label prediction and out-of-distribution generalization' (NeurIPS 2022), 'Non-i.i.d. multi-instance learning for predicting instance and bag labels using variational auto-encoder' (IJCAI 2021), 'Treatment effect estimation with disentangled latent factors' (AAAI 2021), and 'Multi-Instance Learning with Distribution Change' (AAAI 2014). He has earned recognitions such as Top Reviewer Awards from AAAI (2021), Conference on Uncertainty in Artificial Intelligence (2022), and NeurIPS (2025), the Best Master Thesis Award from Nanjing University's Department of Computer Science and Technology (2014), 2nd place in the DREAM Data Mining Challenge on Disease Module Identification (2016), 2nd place in the 3 Minute Thesis Competition at the University of South Australia (2016), and scholarships including the University President’s Scholarship and ITMS Scholarship from the University of South Australia (2014). At the University of Newcastle, he coordinates and lectures courses such as STAT1060 Business Decision Making, STAT3040 Time Series Forecasting, and STAT6160 Data Analytics for Business Intelligence.