Jing Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jing Li has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jinliang Li
School of Economics and Management, Tsinghua University, Beijing, Beijing, China
3 shared publications - Paolo Trucco
Politecnico di Milano, Milan, Italy
3 shared publications - Qian Cao
Politecnico di Milano
3 shared publications - Guangzhe Zhao
School of Intelligence Science and Technology, Beijing University of Civil Engineering and Architecture, Beijing, China
1 shared publication - He Liu1 shared publication
- Hongyin Shi
Beijing University of Civil Engineering and Architecture
1 shared publication
Latest Publications
- 21 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Fast online learning algorithm based on modified hierarchical Unimodal Thompson Sampling
- 21 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Fast online learning algorithm based on modified hierarchical Unimodal Thompson Sampling
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1384-1385
Web-Mined Hypothesis Generation for Financial Markets: An Autonomous Backtesting Framework
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1384-1385
Open AccessWeb-Mined Hypothesis Generation for Financial Markets: An Autonomous Backtesting Framework
- Open Access
- 5 February 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (3) , 1606
Sustainability-Oriented Urban Traffic System Optimization Through a Hierarchical Multi-Agent Deep Reinforcement Learning Framework
Urbanization is intensifying congestion, emissions, and unequal mobility access in cities. This study aims to operationalize sustainability objectives—efficiency, environmental externalities, and service equity—in network-wide traffic system control. We propose SERL-H, a sustainability-aware hierarchical multi-agent reinforcement learning (MARL) controller. SERL-H separates fast intersection-level actuation from slower region-level coordination under a centralized-training decentralized-execution paradigm, and employs adaptive graph attention to capture time-varying interdependencies with bounded neighborhood communication. The learning reward explicitly balances delay/throughput, emissions/fuel, and an equity regularizer based on service dispersion across user groups. In a SUMO-based city-scale simulation with 100 signalized intersections, SERL-H reduces average delay from 45 s to 29 s and average travel time from 120 s to 88 s relative to fixed-time control, while increasing throughput and lowering total emissions (4800 kg to 3950 kg). A socio-economic assessment suggests higher annualized cost savings (e.g., $50.27 M/year to $65.91 M/year) and improved environmental quality indices. We also report, as supporting evidence, an optional sustainability-enhanced spatio-temporal graph predictor (SUT-GNN) that provides reliable short-horizon forecasts during peak-hour volatility.
- 5 February 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (3) , 1606
Open AccessSustainability-Oriented Urban Traffic System Optimization Through a Hierarchical Multi-Agent Deep Reinforcement Learning Framework
Urbanization is intensifying congestion, emissions, and unequal mobility access in cities. This study aims to operationalize sustainability objectives—efficiency, environmental externalities, and service equity—in network-wide traffic system control. We propose SERL-H, a sustainability-aware hierarchical multi-agent reinforcement learning (MARL) controller. SERL-H separates fast intersection-level actuation from slower region-level coordination under a centralized-training decentralized-execution paradigm, and employs adaptive graph attention to capture time-varying interdependencies with bounded neighborhood communication. The learning reward explicitly balances delay/throughput, emissions/fuel, and an equity regularizer based on service dispersion across user groups. In a SUMO-based city-scale simulation with 100 signalized intersections, SERL-H reduces average delay from 45 s to 29 s and average travel time from 120 s to 88 s relative to fixed-time control, while increasing throughput and lowering total emissions (4800 kg to 3950 kg). A socio-economic assessment suggests higher annualized cost savings (e.g., $50.27 M/year to $65.91 M/year) and improved environmental quality indices. We also report, as supporting evidence, an optional sustainability-enhanced spatio-temporal graph predictor (SUT-GNN) that provides reliable short-horizon forecasts during peak-hour volatility.
- 3 April 2025
- Published by Springer Nature
- p. 209-224
Optimizing Intelligent Transportation Systems with Multi-agent Reinforcement Learning: A Socio-economic Impact Assessment
- 3 April 2025
- Published by Springer Nature
- p. 209-224
Optimizing Intelligent Transportation Systems with Multi-agent Reinforcement Learning: A Socio-economic Impact Assessment
- 12 March 2025
- Published by Springer Nature
- p. 406-415
Modeling Interdependencies in Intelligent Traffic Systems and Sustainable Urban Development Using Graph Neural Networks
- 12 March 2025
- Published by Springer Nature
- p. 406-415
Modeling Interdependencies in Intelligent Traffic Systems and Sustainable Urban Development Using Graph Neural Networks
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 222-230
DiffusionE: Reasoning on Knowledge Graphs via Diffusion-based Graph Neural Networks
Graph Neural Networks (GNNs) have demonstrated powerful capabilities in reasoning within Knowledge Graphs (KGs), gathering increasing attention. Our idea stems from the observation that the prior work typically employs hand-designed or sample-designed paradigms in the process of message propagation, engaging a set of adjacent entities at each step of propagation. As a result, such methods struggle with the increasing number of entities involved as propagation steps extend. Moreover, they neglect the message interactions between adjacent entities and propagation relations in KG reasoning, leading to semantic inconsistency during the message aggregation phase. To address these issues, we introduce a novel knowledge graph embedding method through a diffusion process, termed DiffusionE. Specifically, we reformulate the message propagation in knowledge reasoning as a diffusion process, regarding the message semantics as the diffusion signal. In this sense, guided by semantic information, messages can be transmitted between nodes effectively and adaptively. Furthermore, the theoretical analysis suggests our method can leverage an optimal diffusivity for message propagation in the semantic interactions of KGs. It shows that DiffusionE effectively leverages message interactions between entities and propagation relations, ensuring semantic consistency in KG reasoning. Comprehensive experiments reveal that our method attains state-of-the-art performance compared to prior work on several well-established benchmarks.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 222-230
Open AccessDiffusionE: Reasoning on Knowledge Graphs via Diffusion-based Graph Neural Networks
Graph Neural Networks (GNNs) have demonstrated powerful capabilities in reasoning within Knowledge Graphs (KGs), gathering increasing attention. Our idea stems from the observation that the prior work typically employs hand-designed or sample-designed paradigms in the process of message propagation, engaging a set of adjacent entities at each step of propagation. As a result, such methods struggle with the increasing number of entities involved as propagation steps extend. Moreover, they neglect the message interactions between adjacent entities and propagation relations in KG reasoning, leading to semantic inconsistency during the message aggregation phase. To address these issues, we introduce a novel knowledge graph embedding method through a diffusion process, termed DiffusionE. Specifically, we reformulate the message propagation in knowledge reasoning as a diffusion process, regarding the message semantics as the diffusion signal. In this sense, guided by semantic information, messages can be transmitted between nodes effectively and adaptively. Furthermore, the theoretical analysis suggests our method can leverage an optimal diffusivity for message propagation in the semantic interactions of KGs. It shows that DiffusionE effectively leverages message interactions between entities and propagation relations, ensuring semantic consistency in KG reasoning. Comprehensive experiments reveal that our method attains state-of-the-art performance compared to prior work on several well-established benchmarks.
- 19 February 2023
- Published by Springer Nature
- p. 429-444
Mimic Octopus Attack: Dynamic Camouflage Adversarial Examples Using Mimetic Feature for 3D Humans
- 19 February 2023
- Published by Springer Nature
- p. 429-444
Mimic Octopus Attack: Dynamic Camouflage Adversarial Examples Using Mimetic Feature for 3D Humans