Research Interest

I study behaviors in dynamical and structural systems, and how to estimate and control them. Recently I focus on cross-system behaviors and generalized patterns across very different real-world systems, including traffic grids, power networks, epidemics, social networks, banking, supply chains, and most recently large language models viewed as dynamical systems with structural representations. Techniques I love include spectral / functional analysis and uncertainty quantification (UQ).

Relevant support: NSF CAREER #2443266 · NSF CIRC #2345921 · all grants →

Generalized patterns across systems

① "Analogy learning": Generalized patterns across systems. I look for shared operators, conserved quantities, and structural invariants that transfer across otherwise unrelated graph domains.

Cross-system behaviors

② "Interplay learning": Cross-system behaviors. I model and control behaviors that propagate between heterogeneous networks, where the most consequential dynamics live in the cross-edges.

Selected Paper

Full publication

Marouane Benbrahim, Xin Fang, and Zhiqian Chen. “Sumo x PyPSA: Interactive Web Demo of Real-Time Urban Power-Traffic Co-Simulation with Vehicle-to-Grid.” Proceedings of the ACM Web Conference, 2026. papercode Cross-Network CORE A*

Zirui Yuan, Minglai Shao, and Zhiqian Chen. “Graph bayesian optimization for multiplex influence maximization.” Proceedings of the AAAI Conference on Artificial Intelligence, 2024. papercode Cross-Network CORE A*

Lei Zhang, Zhiqian Chen, Chang-Tien Lu, and Liang Zhao. “Network Interdiction Goes Neural.” Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2025. paper Cross-Network CORE A*

Zonghan Zhang and Zhiqian Chen. “Sobol's Total Indices for Accurate and Scalable Feature Exclusion in High-Dimensional Data.” 2025 IEEE International Conference on Big Data (BigData), 2025. paper UQ CORE B

T. Rashme, Z. Zhang, J. Weeks, others, and Zhiqian Chen. “Graph symbolic regression to interpret the propagation of Vesicular Stomatitis Virus across the US and Mexico.” Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems, 2025. paper Symbolic CORE A

Zijian Zhang, Zonghan Zhang, and Zhiqian Chen. “Multiple-Source Localization from a Single-Snapshot Observation Using Graph Bayesian Optimization.” Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 20, 2024: 22538–22546. papercodedoi UQ CORE A*

Taoran Ji, Nathan Self, Kaiqun Fu, Zhiqian Chen, Naren Ramakrishnan, and Chang-Tien Lu. “Citation Forecasting with Multi-Context Attention-Aided Dependency Modeling.” ACM Transactions on Knowledge Discovery from Data, 2024. paper innovation

K. Napier, T. Bhowmik, and Zhiqian Chen. “Explaining poor performance of text-based machine learning models for vulnerability detection.” Empirical Software Engineering, 2024. paper Software/Hardware

Zonghan Zhang and Zhiqian Chen. “Understanding Influence Maximization via Higher-Order Decomposition.” Proceedings of the 2023 SIAM International Conference on Data Mining (SDM), 2023. paper UQ CORE A

Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Lingfei Wu, Charu Aggarwal, and Chang-Tien Lu. “Bridging the gap between spatial and spectral domains: A unified framework for graph neural networks.” ACM Computing Surveys, 2023. paper Spectral Graph

Guangyu Meng, Qisheng Jiang, Kaiqun Fu, Beiyu Lin, Chang-Tien Lu, and Zhqian Chen. “Early forecasting of the impact of traffic accidents using a single shot observation.” Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), 2022. paper Spatial CORE A

Taoran Ji, Nathan Self, Kaiqun Fu, Zhiqian Chen, Naren Ramakrishnan, and Chang-Tien Lu. “Dynamic Multi-Context Attention Networks for Citation Forecasting of Scientific Publications.” Proceedings of the AAAI Conference on Artificial Intelligence, 2021. paper innovation CORE A*

Fanglan Chen, Zhiqian Chen, Subhodip Biswas, Shuo Lei, Naren Ramakrishnan, and Chang-Tien Lu. “Graph convolutional networks with kalman filtering for traffic prediction.” Proceedings of the 28th International Conference on Advances in Geographic Information Systems, 2020. paper Spatial CORE A

Subhodip Biswas, Fanglan Chen, Zhiqian Chen, Chang-Tien Lu, and Naren Ramakrishnan. “Incorporating domain knowledge into memetic algorithms for solving spatial optimization problems.” Proceedings of the 28th International Conference on Advances in Geographic Information Systems, 2020. paper Spatial Best Paper Award CORE A

Zhiqian Chen, Gaurav Kolhe, Setareh Rafatirad, Chang-Tien Lu, Sai Manoj PD, Houman Homayoun, and Liang Zhao. “Estimating the circuit de-obfuscation runtime based on graph deep learning.” 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020. paper Software/Hardware CORE A

Ying Zhang, Xingfeng He, Zhiqian Chen, Qiang Bai, Adelaide M Nolan, Charles A Roberts, Debasish Banerjee, Tomoya Matsunaga, Yifei Mo, and Chen Ling. “Unsupervised discovery of solid-state lithium ion conductors.” Nature Communications, 2019. paper Material Sci. Top 50 Chemistry & Materials Sciences article

Zhiqian Chen, Feng Chen, Rongjie Lai, Xuchao Zhang, and Chang-Tien Lu. “Rational neural networks for approximating graph convolution operator on jump discontinuities.” 2018 IEEE International Conference on Data Mining (ICDM), 2018. paper Spectral Graph CORE A

Zhiqian Chen, Chih-Wei Wu, Yen-Cheng Lu, Alexander Lerch, and Chang-Tien Lu. “Learning to fuse music genres with generative adversarial dual learning.” 2017 IEEE International Conference on Data Mining (ICDM), 2017. papercode Music CORE A

Selected Repo

Full repo

Spectral Graph

Survey-driven entry point to spectral graph theory, graph signals, and modern graph learning.

owner XGraph-Team language Python

Fusion GAN

Music generation project on genre fusion with adversarial dual learning.

owner XGraph-Team language Python

XFlow

Python library for graph flow simulation, diffusion, and network dynamics experiments.

owner XGraph-Team language Python

SumoXPypsa

Coupled transportation-power simulation stack behind the WWW 2026 line of work.

owner XGraph-Team language Python