QWQianni Wang

Qianni Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Qianni Wang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:

  • Yu (Marco) Nie

    Department of Civil and Environmental Engineering, Northwestern University, Evanston, Illinois 60208

    5 shared publications
  • Jiayang Li

    Department of Data and Systems Engineering, The University of Hong Kong, Hong Kong SAR, China

    4 shared publications
  • Jun Xie

    School of Transportation and Logistics, Southwest Jiaotong University, Chengdu 610032, China

    4 shared publications
  • Liyang Feng

    Southwest Jiaotong Univ, Sch Transportat & Logist, Chengdu, Peoples R China

    2 shared publications
  • Boyi Liu

    Department of Industrial Engineering and Management Science, Northwestern University, Evanston, Illinois 60208

    1 shared publication
  • Hongtai Yang

    School of Transportation and Logistics, National Engineering Laboratory of Integrated Transportation Big Data Application Technology, National United Engineering Laboratory of Integrated and Intelligent Transportation, Institute of System Science and Engineering, Southwest Jiaotong University, Chengdu 611756, China

    1 shared publication

Latest Publications

  • Differentiable Bilevel Programming for Stackelberg Congestion Games

    by Jiayang Li, Jing Yu, Qianni Wang, Boyi Liu, Zhaoran Wang, Yu (Marco) Nie

    In a Stackelberg congestion game (SCG), a leader aims to maximize their own gain by anticipating and manipulating the equilibrium state at which the followers settle by playing a congestion game. Often formulated as bilevel programs, large-scale SCGs are well known for their intractability and complexity. Here, we attempt to tackle this computational challenge by marrying traditional methodologies with the latest differentiable programming techniques in machine learning. The core idea centers on replacing the lower-level equilibrium problem with a smooth evolution trajectory defined by the imitative logit dynamic (ILD), which we prove converges to the equilibrium of the congestion game under mild conditions. Building upon this theoretical foundation, we propose two new local search algorithms for SCGs. The first is a gradient descent algorithm that obtains the derivatives by unrolling ILD via differentiable programming. Thanks to the smoothness of ILD, the algorithm promises both efficiency and scalability. The second algorithm adds a heuristic twist by cutting short the followers’ evolution trajectory. Behaviorally, this means that instead of anticipating the followers’ best response at equilibrium, the leader seeks to approximate that response by only looking ahead a limited number of steps. Our numerical experiments are carried out over various instances of classic SCG applications ranging from toy benchmarks to large-scale real-world examples. The results show that the proposed algorithms are reliable and scalable local solvers that deliver high-quality solutions with greater regularity and significantly less computational effort compared with the many incumbents included in our study. Funding: This research is funded by the National Natural Science Foundation of China’s Young Scientists Fund (Type C) [Grant 72501242], the U.S. National Science Foundation’s Civil Infrastructure System Program [Grant CMMI 2225087], and the Energy, Power, Control, and Networks Program [Grant ECCS 2048075]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2026.0233 .

  • Can Information Design Resolve Electric Vehicle Charging Chaos?

    by Qianni Wang, Xiaotong Sun, Yu (Marco) Nie, Jiayang Li

    Charging remains an obstacle to the mass adoption of electric vehicles (EVs), especially for long-distance travel. If many EV drivers take to the road around the same time, their “range anxiety” may create a self-fulfilling prophecy. As drivers anticipate uncertainty and congestion at charging stations, they tend to make decisions about when and where to charge that could collectively lead to chaos and inefficiency. Here, we show that information design can persuade drivers to adopt decisions that are better for the system while being consistent with their self-interest as defined by the Bayesian Nash equilibrium. Our stylized model incorporates a congestion effect into drivers’ payoffs and assumes that the information designer can leverage its private knowledge about the charging condition to influence heterogeneous drivers whose type is defined by their vehicle’s remaining range. We consider both public and private information designs. The former does not depend on the driver type, whereas the latter does. For the private design problem, we propose a novel cutoff structure that enables us to reformulate an infinite-dimensional problem as a finite one. Our analysis shows that, in a one-station, two-state model equipped with a linear cost function, the optimal public design reduces to full information revelation. Moreover, the optimal private design within the proposed cutoff-based class yields significantly better outcomes and, in some cases, can even attain the system optimum. The model is further extended to a corridor setting to examine the impact of different information release schedules. Numerical results show that the private design with sequential release consistently yields the best performance. Under public design, however, the relative effectiveness of different release schedules depends on the spatial configuration of the corridor, among other factors. Funding: This research is supported by the U.S. National Science Foundation’s Civil Infrastructure System (CIS) Program [Grant CMMI #2225087]. J. Li is supported by the National Natural Science Foundation of China [Grant 72501242]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2025.0017 .


  • An Efficient Algorithm for Continuous Bi-Criteria Traffic Assignment

    by Jun Xie, Qianni Wang, Jiayang Li, Yu (Marco) Nie

    Computing Equilibrium with Heterogeneous User Preferences The authors address a long-standing challenge in transportation network modeling: how travelers choose routes in congested networks when balancing multiple route attributes, some of which are naturally continuous. Their new algorithm decomposes this complex problem into a sequence of intuitive route-level adjustments based on implicit boundaries of continuous attributes. This enables the model to capture detailed route-level decisions that have been difficult to compute at scale in such settings. The results show that the new method significantly outperforms existing approaches, often delivering speedups of an order of magnitude. Beyond computational gains, the study also establishes rigorous convergence guarantees and demonstrates the advantages of working directly with a continuous formulation as opposed to conventional discretization-based methods. The work opens the door to more realistic and scalable modeling of transportation systems with behaviorally heterogeneous users.


  • Entropy maximization in multi-class traffic assignment

    by Qianni Wang, Liyang Feng, Jiayang Li, Jun Xie, Yu (Marco) Nie


  • Open Access

    A Class of Efficient Algorithms for the Bi-Level Demand Adjustment Problems in Congested Traffic Networks

    by Lan Cheng, Jun Xie, Jun Huang, Liyang Feng, Qianni Wang, Hongtai Yang

    This paper studies a class of gradient-descent heuristic algorithms for the bi-level demand adjustment problem (DAP), which seeks to adjust origin-destination (OD) matrices based on observed link flows in congested transportation networks. We first present a general gradient-descent solution framework for the bi-level DAP and then examine and further develop its two building blocks, namely, the gradient approximation and stepsize calculation. This paper presents two gradient approximation and four stepsize calculation methods, of which two stepsize methods are newly developed. Similarities and differences between these algorithms, as well as the relevant implementation issues are discussed in great detail. The numerical results show that algorithms employing the new stepsize calculation strategies consistently outperform existing algorithms in terms of both computational precision and efficiency.