Haowei Xu 徐皓玮

Peking University Ph.D. Student, Institute of Medical Technology, Peking University

I am a Ph.D. student in the Medical Innovation Interdisciplinary Program at the Institute of Medical Technology, Peking University Health Science Center. My research focuses on scientific machine learning for simulation, control, design, and discovery of neuronal cell microenvironments. My interests include AI4Science, virtual cells, neural operators, and generative models. I am supervised by Prof. Zhaoheng Xie (Principal Supervisor, algorithmic guidance) and Prof. Hongbin Han (Co-Supervisor, funding and neuroscience guidance).


News
2025
Nov 09
Our paper “Subphenotype Identification for Sepsis-Associated Acute Kidney Injury using Graph Bidirectional Mamba Networks” has been accepted by IEEE Journal of Biomedical and Health Informatics (IEEE J-BHI, JCR Q1, IF: 6.8)
May 21
Our paper “Neural Granger Causal Discovery for Derangements in ICU-Acquired Acute Kidney Injury Patients” has been accepted by AMIA Annual Symposium Proceedings (AMIA)
May 11
Our paper “SIGRL: Sociologically-Informed Graph Representation Learning for Social Influence Prediction” has been accepted by IEEE Transactions on Network Science and Engineering (IEEE T-NSE, CCF-B, JCR Q1, IF: 6.9)
Apr 10
Our paper “Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference” has been accepted by AAAI Conference on Artificial Intelligence (AAAI, CCF-A)
Mar 09
Our paper “D2: Customizing Two-Stage Graph Neural Networks for Early Rumor Detection through Cascade Diffusion Prediction” has been accepted by Web Search and Data Mining (WSDM, CCF-B)
Jan 14
Our paper “HyperIDP: Customizing Temporal Hypergraph Neural Networks for Multi-Scale Information Diffusion Prediction” has been accepted by International Conference on Computational Linguistics (COLING, CCF-B)
2024
Dec 14
JD Health Global Medical AI Innovation Competition — Top 5%
Sep 17
Our paper “RumorMixer: Exploring Echo Chamber Effect and Platform Heterogeneity for Rumor Detection” has been accepted by European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD, CCF-B)
Apr 19
Harvard Medical School Harmful Brain Activity Classification — Silver Medal
Mar 09
19th “Challenge Cup” Revealing Champion Special Competition — National First Prize
Selected Publications (view all )
Subphenotype Identification for Sepsis-Associated Acute Kidney Injury using Graph Bidirectional Mamba Networks

Haowei Xu, Wentie Liu, Tongyue Shi, Guilan Kong

IEEE Journal of Biomedical and Health Informatics 2025 Journal

We introduce a bidirectional Mamba-based graph learning framework that uncovers clinically meaningful subphenotypes for sepsis-associated acute kidney injury by modeling multimodal EHR dynamics and cross-patient relationships.

Subphenotype Identification for Sepsis-Associated Acute Kidney Injury using Graph Bidirectional Mamba Networks
Subphenotype Identification for Sepsis-Associated Acute Kidney Injury using Graph Bidirectional Mamba Networks

Haowei Xu, Wentie Liu, Tongyue Shi, Guilan Kong

IEEE Journal of Biomedical and Health Informatics 2025 Journal

We introduce a bidirectional Mamba-based graph learning framework that uncovers clinically meaningful subphenotypes for sepsis-associated acute kidney injury by modeling multimodal EHR dynamics and cross-patient relationships.

Neural Granger Causal Discovery for Derangements in ICU-Acquired Acute Kidney Injury Patients

Haowei Xu, Wentie Liu, Tongyue Shi, Guilan Kong

AMIA Annual Symposium Proceedings 2025 Conference

This work discovers causal pathways driving acute kidney injury in the ICU by pairing neural Granger causality with temporal multimodal measurements, enabling actionable risk stratification for critical care teams.

Neural Granger Causal Discovery for Derangements in ICU-Acquired Acute Kidney Injury Patients
Neural Granger Causal Discovery for Derangements in ICU-Acquired Acute Kidney Injury Patients

Haowei Xu, Wentie Liu, Tongyue Shi, Guilan Kong

AMIA Annual Symposium Proceedings 2025 Conference

This work discovers causal pathways driving acute kidney injury in the ICU by pairing neural Granger causality with temporal multimodal measurements, enabling actionable risk stratification for critical care teams.

SIGRL: Sociologically-Informed Graph Representation Learning for Social Influence Prediction

Haowei Xu, Chao Gao, Xingyu Li, Zhihai Wang

IEEE Transactions on Network Science and Engineering 2025 Journal

SIGRL integrates sociological priors into graph representation learning to model influence propagation with improved fidelity across complex social interaction networks.

SIGRL: Sociologically-Informed Graph Representation Learning for Social Influence Prediction
SIGRL: Sociologically-Informed Graph Representation Learning for Social Influence Prediction

Haowei Xu, Chao Gao, Xingyu Li, Zhihai Wang

IEEE Transactions on Network Science and Engineering 2025 Journal

SIGRL integrates sociological priors into graph representation learning to model influence propagation with improved fidelity across complex social interaction networks.

D2: Customizing Two-Stage Graph Neural Networks for Early Rumor Detection through Cascade Diffusion Prediction

Haowei Xu, Chao Gao, Xingyu Li, Zhihai Wang

WSDM 2025 Conference

We design a diffusion-aware dual-stage graph neural network that anticipates rumor spread patterns and flags misinformation during its early cascade evolution across social platforms.

D2: Customizing Two-Stage Graph Neural Networks for Early Rumor Detection through Cascade Diffusion Prediction
D2: Customizing Two-Stage Graph Neural Networks for Early Rumor Detection through Cascade Diffusion Prediction

Haowei Xu, Chao Gao, Xingyu Li, Zhihai Wang

WSDM 2025 Conference

We design a diffusion-aware dual-stage graph neural network that anticipates rumor spread patterns and flags misinformation during its early cascade evolution across social platforms.

RumorMixer: Exploring Echo Chamber Effect and Platform Heterogeneity for Rumor Detection

Haowei Xu, Chao Gao, Xingyu Li, Zhihai Wang

ECML-PKDD 2024 Conference

RumorMixer disentangles echo chambers and cross-platform heterogeneity through a multi-view graph design, enabling robust rumor detection in diverse social media ecosystems.

RumorMixer: Exploring Echo Chamber Effect and Platform Heterogeneity for Rumor Detection
RumorMixer: Exploring Echo Chamber Effect and Platform Heterogeneity for Rumor Detection

Haowei Xu, Chao Gao, Xingyu Li, Zhihai Wang

ECML-PKDD 2024 Conference

RumorMixer disentangles echo chambers and cross-platform heterogeneity through a multi-view graph design, enabling robust rumor detection in diverse social media ecosystems.

All publications
Roadmap

My doctoral research framework focuses on Simulation, Control, Design and Discovery of Neuronal Cell Microenvironment via Scientific Machine Learning. The roadmap highlights the interplay between data curation, model design, and translational evaluation pipelines.

Doctoral research roadmap
Projects & Interests

My research spans scientific machine learning and computational healthcare, with particular emphasis on neuronal cell microenvironment modeling, AI4Science methodologies, and generative approaches for biological systems.

AI4Science AI4PDE Virtual Cells Neural Operators Generative Models

Education
  • Peking University Health Science Center

    Peking University Health Science Center

    Institute of Medical Technology

    Ph.D. Candidate in Medical Imaging Technology Sep. 2025 - Jun. 2028

  • Northwestern Polytechnical University

    Northwestern Polytechnical University

    Institute of Optics and Intelligent Sensing

    M.Eng. in Computer Science and Technology Sep. 2022 - Mar. 2025

  • Northwest A&F University

    Northwest A&F University

    College of Information Engineering

    B.Eng. in Information Management and Information Systems Sep. 2018 - Jun. 2022

Honors & Awards
  • 19th “Challenge Cup” Revealing Champion Special Competition — National First Prize 2024
  • National Postgraduate Mathematical Modeling Competition — Second Prize 2023
  • National Postgraduate Mathematical Modeling Competition — Second Prize 2022
  • ICM/MCM Mathematical Contest in Modeling — International Finalist (Outstanding Winner Nomination) 2021
Competitions
  • JD Health Global Medical AI Innovation Competition — Top 5% 2024
  • Harvard Medical School Harmful Brain Activity Classification — Silver Medal 2024
Experience
  • National Institute of Health Data Science, Peking University

    National Institute of Health Data Science, Peking University

    Prof. Guilan Kong's Research Group

    Research Assistant Dec. 2023 - Dec. 2024

Service
  • Reviewer, IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
  • Reviewer, IEEE Transactions on Network Science and Engineering (IEEE T-NSE)
  • Reviewer, International World Wide Web Conference (WWW)
  • Reviewer, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
  • Reviewer, International Joint Conference on Artificial Intelligence (IJCAI)
  • Reviewer, International Conference on Machine Learning (ICML)
Contact

Preferred channels for collaboration and inquiries.