Suqi Liu

I am a Postdoctoral Research Fellow in Biomedical Informatics at Harvard University working with Professor Tianxi Cai. I received my Ph.D. from Princeton University advised by Professor Miklos Racz. My research interests range from the theoretical foundations to the practical applications of probability, statistics, machine learning, and data science. Specifically, I focus on complex structured health data, including biomedical networks, genomic sequences, and clinical notes.

Previously, I was a graduate student at UC San Diego advised by Professor Lawrence Saul, co-advised by Professor Geoffrey Voelker and Professor Stefan Savage. I completed my undergraduate degree at Tsinghua University with my thesis supervised by Professor Jun Zhu. I did internships at Google Knowledge Graph and Ads AI teams in 2016 and 2018 respectively. I was also a research intern at Microsoft Research Asia Machine Learning Group from April to November 2012.

Education

• Ph.D. in Operations Research and Financial Engineering, Princeton University, 2016–2022.

• M.S. in Computer Science, University of California, San Diego, 2013–2016.

• B.S. in Mathematics and Physics, Tsinghua University, 2009–2013.

Publications

Preprints

• Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning

Hongyi Yuan, Suqi Liu, Kelly Cho, Katherine Liao, Alexandre Pereira, Tianxi Cai

arXiv:2410.10144

• Representation-Enhanced Neural Knowledge Integration with Application to Large-Scale Medical Ontology Learning

Suqi Liu, Tianxi Cai, Xiaoou Li

arXiv:2410.07454

• Random Geometric Graph Alignment with Graph Neural Networks
  Suqi Liu and Morgane Austern
  arXiv:2402.07340

Journal papers

• A probabilistic view of latent space graphs and phase transitions
  Suqi Liu and Miklos Z. Racz
  Bernoulli 29 (3), 2417-2441 (2023).
  arXiv:2110.15886

• Phase transition in noisy high-dimensional random geometric graphs
  Suqi Liu and Miklos Z. Racz
  Electronic Journal of Statistics 17 (2), 3512-3574 (2023).
  arXiv:2103.15249

Conference and workshop papers

• Modeling Advertiser Bidding Behaviors in Google Sponsored Search with a Mirror Attention Mechanism
  Suqi Liu, Liang Liu, Sugato Basu, Jean-Francois Crespo
  AdKDD 2019

• Who is .com? Learning to Parse WHOIS Records
  Suqi Liu, Ian Foster, Stefan Savage, Geoffrey M. Voelker, Lawrence K. Saul
  Internet Measurement Conference (IMC) 2015

Theses

• Geometry of Random Graphs
  Ph.D. thesis, Princeton University, May 2022.
  Advisor: Miklos Z. Racz
  Committee: Miklos Z. Racz (Chair), Mykhaylo Shkolnikov, and Ramon van Handel

• Max-Margin Sum-Product Networks
  Diploma thesis, Tsinghua University, June 2013.
  Advisor: Jun Zhu

Talks

• Random Geometric Graph Matching with Graph Neural Networks. INFORMS Annual Meeting, October 23, 2024.

• Representation-Enhanced Neural Knowledge Integration. DBMI Science Day, Harvard, September 12, 2024.

• Random Geometric Graph Matching with Graph Neural Networks. Joint Statistical Meetings, August 7, 2024.

• Random Geometric Graph Matching with Graph Neural Networks. IDEAL Workshop on Learning in Networks: Discovering Hidden Structure, April 10, 2024.

• Multimodal Representation Learning of Clinical Concepts and Genetic Variants. MVP Science Meeting, U.S. Department of Veterans Affairs, October 30, 2023.

• Phase transitions in soft random geometric graphs. Graduate Student Seminar, PACM, Princeton, March 15, 2022.

• Phase transitions in soft random geometric graphs. Stochastics Seminar, School of Mathematics, Georgia Tech, January 13, 2022.

• A probabilistic view of latent space graphs and phase transitions. Northeast Probability Seminar, November 18, 2021. [video] [slides]

• Phase transition in noisy high-dimensional random geometric graphs. Columbia–Princeton Probability Day, May 7, 2021. [video] [slides]

• Learning to parse WHOIS records. Internet Measurement Conference, Oct 30, 2015. [slides]

Teaching

• Assistant in Instruction, ORF 309 (Probability and Stochastic Systems), Princeton, Spring 2022.

• Assistant in Instruction, ORF 526 (Probability Theory), Princeton, Fall 2018, Fall 2019, Fall 2020.

• Assistant in Instruction, ORF 387 (Networks), Princeton, Spring 2020, Spring 2021.

• Assistant in Instruction, ORF 350 (Analysis of Big Data), Princeton, Fall 2017, Spring 2019.

• Assistant in Instruction, ORF 307 (Optimization), Princeton, Spring 2018.

• Teaching Assistant, CSE 250A (Principles of Artificial Intelligence), UCSD, Spring 2016.

• Teaching Assistant, CSE 150A (Introduction to Artificial Intelligence), UCSD, Winter 2016.