Lecheng Zheng

Presidential Postdoctoral Fellow · Virginia Tech

Heterogeneous Machine Learning · Trustworthy AI · AI for Science

I am a Presidential Postdoctoral Fellow at Pamplin College of Business, Virginia Tech, working with Prof. Jian Ni and Prof. Christopher Zobel. I received my Ph.D. in Computer Science from the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Jingrui He.

My research focuses on heterogeneous machine learning, with an emphasis on developing generalizable and trustworthy AI methods for complex, real-world problems. I work on graph learning, multimodal representation learning, and foundation models, with applications in AI for Science, cybersecurity, digital infrastructure, finance, and healthcare. My long-term goal is to develop adaptive AI systems that can learn from heterogeneous information and support reliable reasoning and decision-making across domains.

At Virginia Tech, I extend my machine learning research through interdisciplinary collaborations in economic networks, financial risk analytics, and intelligent decision-making.

I am seeking tenure-track faculty positions in computer science, data science, and related areas for the 2026–2027 academic hiring cycle.

Portrait of Lecheng Zheng

Research Vision

My long-term goal is to develop adaptive and trustworthy intelligence that can understand heterogeneous information and generalize to changing, real-world settings.

Research vision figure showing a heterogeneous intelligence framework from heterogeneous observations and evidence to characterization, generalization, and decision-making across domains.
My research vision centers on a heterogeneous intelligence framework that moves from heterogeneous observations and evidence to characterization, generalization, and decision-making, with applications in cybersecurity, finance, digital infrastructure, healthcare, and scientific systems.

Application Domains

The framework connects common learning challenges to five real-world domains illustrated above.

Digital Infrastructure

Multimodal diagnosis, root-cause analysis, and reliable distributed systems.

Financial Networks

Economic networks, financial forecasting, risk analytics, and incentive design.

Cybersecurity

Graph anomaly detection and collaborative, federated security analytics.

Scientific Systems

Climate modeling, scientific time series, and AI for Science.

Healthcare

Biomedical language understanding, retrieval, and multi-label learning.

Recent milestones

News

Research leadership

Research Funding

Funded projects where I serve as principal investigator or co-principal investigator. Amounts are total award values.

Incentive-Compatible Federated Risk Detection for Cross-Institution Security Networks

Commonwealth Cyber Initiative (CCI-SWVA) · External grant · 2026

$14,999 Principal Investigator

AI-Powered Economic Network Analytics: Integrating Consumer Behavior Models with Graph Learning to Combat Financial Fraud

Pamplin Duo+ Seed Grant · Internal grant · 2025–2027

$25,000 Co-Principal Investigator

AgriMind: A Multi-Modal AI Framework for Weather-Robust and Market-Adaptive Precision Agriculture

Virginia Tech FY26 CALS · Internal grant · 2026–2028

$75,000 Co-Principal Investigator

Proposals Under Review: Co-PI on two NSF research proposals, including one currently under consideration for a funding recommendation.

Selected Publications

Representative peer-reviewed papers, grouped by primary methodological contribution. A complete publication record is available on Google Scholar and in my CV. Equal-contribution authors are marked with *.

Heterogeneous Representation Learning

Learning from diverse modalities, views, labels, and tasks.

Generalization & Trustworthy Graph Learning

Robust, transferable, interpretable, and fair learning on graphs.

Reasoning, Decision-Making & Intelligent Systems

Causal reasoning, system diagnosis, incentive mechanisms, and learning-enabled decision support.

Foundation Models & Language Intelligence

Connecting heterogeneous learning to language, temporal models, and foundation models.

Recognition

Honors & Awards

Education & student development

Teaching & Mentoring

Teaching

Co-Instructor, Machine Learning (CS 4824)
Virginia Tech · Fall 2025 · ~90 undergraduate students

Shared course instruction and delivered lectures on cluster analysis and heterogeneous machine learning, connecting mathematical foundations with implementation and applications.

Teaching Assistant, Introduction to Data Mining (CS 412)
UIUC · Spring 2022 · 180+ students

Supported assignments, exam reviews, and graduate student projects.

Research Mentoring

Undergraduate research · Virginia Tech, 2026–present.Mentoring two students in LLM-based financial forecasting through the full research process. Their paper received Best Paper Award Runner-Up at IEEE BigData 2026 Undergraduate & REU Consortium.

Ph.D. research · Virginia Tech, 2026–present.Mentoring a student on graph anomaly detection and independent research development.

Ph.D. research · UIUC, 2024–2026.Mentored biomedical multi-label learning research leading to publications in EMNLP Findings and ACL.

Professional community

Academic Service & Tutorials

Editorial and Reviewing Service

Area Chair:ACL ARR, October 2026 cycle.

Conference reviewing / program committee:ICLR, ICML, NeurIPS, AAAI, ACL, IJCAI, KDD, CIKM, The Web Conference, WSDM, and others.

Journal reviewing:ACM Computing Surveys, ACM TKDD, Data Mining and Knowledge Discovery, IEEE Transactions on Mobile Computing, and others.