Hanchen Wang    |  Publication  |  Misc  | 
highlight; * equal; # correspondence

PostDoc, 2023-

Along my three to four-year PostDoc (with full fellowship), I mainly target challenges in Therapeutic Science, emphasizing Genomics. I focus on developing computation tools for cell atlases, various forms of perturbations (chemical/genetic/optical), cancer, and immunotherapy. I'm keen on advancing novel therapeutic modalities such as RNA, Perturbation, Antibody, CAR-T, TIL etc. In addition, I'm working on general data-driven methods that are applicable across broader fields like Physics and Material Sciences, aiming for substantial scientific, social and industrial impacts. Born in a family of professors, trained in Biology (High School Olympiads), Physics (College), and Machine Learning (PhD), my voyage in AI for Science just starts :)

PhD, in Machine Learning, 2019-2022

During my three-year Ph.D (full fellowship for four years), I first shifted research focus from Physics to AI/ML. I then started working on data including votes from polls and surveys, 3D point clouds, CT/CXR scans, pathological and histological images, molecular and relational graphs, as well as single-cell transcriptomics. I develop methods that can learn structures from these data with weak supervisions. Aside from this, I spared some time on quantum computation and did four internships in tech and biotech (Google -> Amazon -> BioMap -> Iambic). Back in 2019, I co-founded a startup (as the CTO) with Stanford and Berkeley alumni, aimed at transforming electronic medical records via language models, with partnerships among 37 hospitals. Though things didn't work out then, my commitment to harnessing AI's power in Healthcare remains steadfast.
25. Learning from Structured Data with Weak Supervision
Hanchen Wang, University of Cambridge, Doctoral Thesis
24. Deciphering Batch Effects in Single-cell Transcriptomics with Concept Bottlenecks
Hanchen Wang et al., John Marioni#
in submission
23. Long-lived TIL Phenotypes Delineate Clinical Response to Liver Cancer with Adoptive Cell Therapy, Phase I&IIa Trial
Lijun Chen et al., Tian Xia#, Main Figures
in review
22. [Book] Machine Learning Systems: Design and Implementation
Chinese, Tsinghua University Press 2023, Table of Contents
English, in press, Springer 2023, Table of Contents
21. Scientific Discovery in the Age of Artificial Intelligence
Hanchen Wang* et al., Yoshua Bengio, Marinka Zitnik# [Team] >
Nature 2023, accepted before revisions
20. Focalizing regions of relevance facilitates biomarker prediction on histopathological images
Jiefeng Gan*, Hanchen Wang*, et al., Tian Xia# [Team] >
iScience 2023
19. Open Problems in Federated Digital Health
Hanchen Wang, James Zou
in revision, Nature Machine Intelligence
18. Evaluating Self-supervised Learning for Molecular Graph Embeddings
Hanchen Wang*, Jean Kaddour*, Shengchao Liu, Jian Tang, Joan Lasenby, Qi Liu
NeurIPS 2023
17. GraphCG: Unsupervised Discovery of Steerable Factors in Graphs
Shengchao Liu et al.,
in review
16. Augmenting Message Passing by Retrieving Similar Graphs
Dingmin Wang et al.,
ECAI 2023
15. Graph Denoising with Edge Editing
Hanchen Wang, Yunlong Jiao, Jordan Massiah
contributed talk at Amazon Machine Learning Conference 2021
14. Pre-training Molecular Graph Representation with 3D Geometry
Shengchao Liu, Hanchen Wang, Weiyang Liu, Joan Lasenby, Hongyu Guo, Jian Tang
ICLR 2022
13. Matching Point Sets with Quantum Circuits Learning
Hanchen Wang*, M. N.* (in contribution order)
ICASSP 2022, Invited by Editors, with Travel Award
project page  |  code
12. Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
Xiang Bai (Prof.)* Hanchen Wang*, Liya Ma*, Yongchao Xu*, Jiefeng Gan*, ..., Carola Schönlieb#, Tian Xia#
Nature Machine Intelligence 2021
11. Iterative Teaching by Label Synthesis
Weiyang Liu*, Zhen Liu*, Hanchen Wang*, Liam Paul, Bernhard Schölkopf, Adrian Weller
NeurIPS 2021, Spotlight
10. Neural Random Subspace
Yun-Hao Cao, et al.,
Pattern Recognition 2021
9. Unsupervised Point Cloud Pre-training via Occlusion Completion
Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matthew J. Kusner
ICCV 2021
8. An Empirical Study on Learning Fairness Metrics for COMPAS Data with Human Supervision
Hanchen Wang, Nina Grgić-Hlača, Preethi Lahoti, Krishna. P. Gummadi, Adrian. V. Weller
axXiv, presented at NeurIPS HCML 2019, with Travel Award

Undergraduate, in Physics, 2014-2018

In addition to studying Theoretical Physics, I researched next-gen electronic devices such as transistors and solar cells, a field at the nexus of Solid-State Physics, Material Sciences and Electrical Engineering. I primarily worked in Xinran Wang's and Ali Javey's groups. I also accrued experience in the finance sector, initially focusing on bonds before transitioning to roles in quantitative trading of equity and crypto. These diverse experiences ultimately cemented my commitment in advancing Science and Engineering with the aim of improving human life, increasingly leveraging computational tools like AI/ML.
7. Current-controlled Propagation of Spin Waves in Antiparallel, Coupled Domains
Nature Nanotechnology 2019
6. Dopant‐Free Partial Rear Contacts Enabling 23% Silicon Solar Cells
Advanced Energy Materials 2019
5. Stable dopant-free asymmetric heterocontact silicon solar cells with efficiencies above 20%
ACS Energy Letters 2018
4. Negative Capacitance 2D MoS2 Transistors with Sub-60mV/dec Subthreshold Swing over 6 Orders, 250 μA/μm Current Density, and Nearly-Hysteresis-Free
Zhihao Yu*, Hanchen Wang* et al., Xinran Wang
IEDM 2017, Oral, Nanjing University's first IEDM paper
3. Molecular Mechanism of Self-Assembly of Aromatic Oligoamides into Interlocked Double-Helix Foldamers
Journal of Physical Chemistry B 2017
2. Microchannel contacting of crystalline silicon solar cells
Scientific Reports 2017
1. Logical integration device for two-dimensional semiconductor transition metal sulfide
Weisheng Li*, Jian Zhou*, Hanchen Wang* et al.,
Invited, Acta Physica Sinica 2017