Scholar

Hengrui Zhang

Google Scholar ID: iwffiD0AAAAJ

University of Illinois Chicago

Machine LearningSelf-Supervised LearningTabular Deep Learning

Citations & Impact

All-time

Citations

1,678

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

- TabNAT: A Continous-Discrete Joint Generative Framework for Tabular Data, ICML 2025
- TabDiff: a Multi-Modal Diffusion Model for Tabular Data Generation, ICLR 2025
- Unleashing the Potential of Diffusion Models for Incomplete Data Imputation, ICLR 2025
- Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering, NeurIPS 2024
- SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity, arXiv preprint arXiv:2409.09007, 2024
- InfoMLP: Unlocking the Potential of MLPs for Semi-Supervised Learning with Structured Data, CIKM 2024
- OrthoReg: Improving Graph-regularized MLPs via Orthogonality Regularization, CIKM 2024
- Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space, ICLR 2024
- Simplifying and Empowering Transformers for Large-Graph Representations, NeurIPS 2023
- Exploiting Intent Evolution in E-commercial Query Recommendation, KDD 2023
- ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation, CIKM 2022
- M-Mix: Generating Hard Negatives via Multi-sample Mixing for Contrastive Learning, KDD 2022
- Align Representations with Base: A New Approach to Self-Supervised Learning, CVPR 2022

Research Experience

- Ph.D. student in Computer Science at University of Illinois, Chicago
- Involved in multiple research projects, including tabular data generation, incomplete data imputation, and graph contrastive learning

Education

Background

- Research Interests: tabular deep learning, generative tabular data modeling (synthetic tabular data generation and missing data imputation)
- Previous Research: graph deep learning, including Graph Neural Networks and self-supervised learning on graph-structured data

Miscellany