I am a fourth year Ph.D. candidate at School of Information, University of Michigan, Ann Arbor. My advisor is Prof. Qiaozhu Mei. Prior to UMich, I got my Bachelor's degree at Tsinghua University, advised by Prof. Jie Tang.

I'm fascinated in discovering succinct descriptions of objects and their relationships, from which machine learning can benefit with improved computational or statistical efficiency. I'm particularly interested in machine learning models for graph-structured data, a general representation of data. I also work on learning-to-rank, multi-task learning, and off-policy learning.

Please check my Google Scholar and Github.

Sep. 2016 - Now, University of Michigan, Ann Arbor

Ph.D. candidate, School of Information

Advisor: Professor Qiaozhu Mei

Sep. 2012 - Jul. 2016, Tsinghua University

B.Eng., Department of Automation

Advisor: Professor Jie Tang

CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks.

Jiaqi Ma, Bo Chang, Xuefei Zhang, Qiaozhu Mei. Preprint.

Learning-to-Rank with Partitioned Preference: Fast Estimation for the Plackett-Luce Model.

Jiaqi Ma, Xinyang Yi, Weijing Tang, Zhe Zhao, Lichan Hong, Ed H. Chi, Qiaozhu Mei. Preprint.

SODEN: A Scalable Continuous-Time Survival Model through Ordinary Differential Equation Networks.

Weijing Tang*, Jiaqi Ma*, Qiaozhu Mei, Ji Zhu. Preprint.

Towards More Practical Adversarial Attacks on Graph Neural Networks.

Jiaqi Ma*, Shuangrui Ding*, Qiaozhu Mei. To appear in NeurIPS 2020. [Code]

Off-policy Learning in Two-stage Recommender Systems.

Jiaqi Ma, Zhe Zhao, Xinyang Yi, Ji Yang, Minmin Chen, Jiaxi Tang, Lichan Hong, Ed H. Chi.

WWW 2020 (with oral presentation). [Code]

A Flexible Generative Framework for Graph-based Semi-supervised Learning.

Jiaqi Ma*, Weijing Tang*, Ji Zhu, Qiaozhu Mei. NeurIPS 2019. [Code]

SNR: Sub-Network Routing for Flexible Parameter Sharing in Multi-task Learning.

Jiaqi Ma, Zhe Zhao, Jilin Chen, Ang Li, Lichan Hong, Ed H. Chi. AAAI 2019.

Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts.

Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, Ed H. Chi. KDD 2018 (with oral presentation).

DeepCas: An End-to-End Predictor of Information Cascades.

Cheng Li, Jiaqi Ma, Xiaoxiao Guo, Qiaozhu Mei. WWW 2017. [Code]

(* indicates equal contribution.)

Research Assistant, Foreseer Group. University of Michigan, Ann Arbor, MI, USA.

Jun. 2019 - Aug. 2019

Research Intern, Google Brain. Google Inc., Mountain View, CA, USA.

May 2018 - Aug. 2018

Research Intern, Google Brain. Google Inc., Mountain View, CA, USA.

May 2017 - Sep. 2017

Research Intern, Research & Machine Intelligence. Google Inc., Mountain View, CA, USA.

Jul. 2016 - Aug. 2016

Research Intern, Detection, Tracking and Reidentification Group. Megvii Inc. (Face++), Beijing, China.

Email: jiaqima AT umich DOT edu

Address: Office 3332, 105 S State St, Ann Arbor, MI 48109