Manos Papagelis
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Manos Papagelis has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Ali Faraji
York University, Toronto, Ontario, Canada
4 shared publications - Amirhossein Nadiri
Electrical Engineering and Computer Science, York University, Toronto, Ontario, CANADA
4 shared publications - Arian Haghparast
EECS, York University
4 shared publications - Ghadeer Abuoda
Electrical Engineering and Computer Science, York University, Toronto, Ontario, CANADA
4 shared publications - Jing Li
Electrical Engineering and Computer Science, York University, Toronto, Ontario, CANADA
4 shared publications - Gian Alix
EECS, York University
3 shared publications
Latest Publications
- Open Access
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (9) , 1-38
Mobility Network Forecasting: A Trajectory-based Contact Prediction Approach
Predicting human mobility patterns is crucial for various applications, including urban planning, traffic management, and public health. A key challenge in this domain is identifying when and where interactions, or contacts , occur between moving individuals (i.e., objects) based on their recent positions. To address this, we represent object movement using a mobility network , where individuals establish connections when they come into close physical proximity. This network framework enables the analysis of individual interactions within a given time frame, providing valuable insights into mobility dynamics. Traditional methods for predicting future interactions typically focus on predicting static snapshots of the mobility network at future time points. These temporal link prediction methods are limited because they do not provide detailed insights into short-term mobility dynamics. In a mobility network, being able to predict both long-term and short-term contacts is crucial in many scenarios: for instance, health authorities may require daily forecasts to plan resource allocation and anticipate disease spread, whereas emergency response teams rely on hour-by-hour (or even minute-by-minute) predictions for real-time outbreak control. In this article, we present MobiNetForecast , a two‐stage framework that (i) individually predicts each user’s next \( k \) locations using a Transformer‐based decoder with constrained beam search to enforce spatial continuity and (ii) infers future contacts by identifying spatiotemporal co‐locations in the predicted trajectories. By unifying short‐ and long‐term forecasts in a single pipeline, our approach can anticipate both recurring and previously unseen interactions. Empirical evaluation on real‐world ( GeoLife ) and large‐scale synthetic ( SFCO‐3K ) trajectory datasets demonstrates that MobiNetForecast outperforms state‐of‐the‐art temporal link prediction methods (e.g., EvolveGCN , ROLAND , DyTed , AGCRN ) by up to two orders of magnitude in F1‐score, and improves over leading sequence models (e.g., Flashback++ ) by 15–20% on key metrics across multiple granularities. These results validate the effectiveness of trajectory‐driven contact prediction for accurate, multi‐scale mobility network forecasting.- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (9) , 1-38
Open AccessMobility Network Forecasting: A Trajectory-based Contact Prediction Approach
Predicting human mobility patterns is crucial for various applications, including urban planning, traffic management, and public health. A key challenge in this domain is identifying when and where interactions, or contacts , occur between moving individuals (i.e., objects) based on their recent positions. To address this, we represent object movement using a mobility network , where individuals establish connections when they come into close physical proximity. This network framework enables the analysis of individual interactions within a given time frame, providing valuable insights into mobility dynamics. Traditional methods for predicting future interactions typically focus on predicting static snapshots of the mobility network at future time points. These temporal link prediction methods are limited because they do not provide detailed insights into short-term mobility dynamics. In a mobility network, being able to predict both long-term and short-term contacts is crucial in many scenarios: for instance, health authorities may require daily forecasts to plan resource allocation and anticipate disease spread, whereas emergency response teams rely on hour-by-hour (or even minute-by-minute) predictions for real-time outbreak control. In this article, we present MobiNetForecast , a two‐stage framework that (i) individually predicts each user’s next \( k \) locations using a Transformer‐based decoder with constrained beam search to enforce spatial continuity and (ii) infers future contacts by identifying spatiotemporal co‐locations in the predicted trajectories. By unifying short‐ and long‐term forecasts in a single pipeline, our approach can anticipate both recurring and previously unseen interactions. Empirical evaluation on real‐world ( GeoLife ) and large‐scale synthetic ( SFCO‐3K ) trajectory datasets demonstrates that MobiNetForecast outperforms state‐of‐the‐art temporal link prediction methods (e.g., EvolveGCN , ROLAND , DyTed , AGCRN ) by up to two orders of magnitude in F1‐score, and improves over leading sequence models (e.g., Flashback++ ) by 15–20% on key metrics across multiple granularities. These results validate the effectiveness of trajectory‐driven contact prediction for accurate, multi‐scale mobility network forecasting. - Open Access
- 24 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 12 (4) , 1-38
Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
Traffic congestion in urban road networks is marked by longer trip times and higher emissions, especially during peak periods. While the Shortest Path First (SPF) algorithm is optimal for a single vehicle in a static network, it performs poorly in dynamic, multi-vehicle settings, often worsening congestion by routing all vehicles along identical paths. We address dynamic vehicle routing through a multi-agent reinforcement learning (MARL) framework for coordinated, network-aware fleet navigation. We first propose Adaptive Navigation (AN), a decentralized MARL model where each intersection agent provides routing guidance based on (i) local traffic and (ii) neighborhood state modeled using Graph Attention Networks (GAT). To improve scalability in large networks, we further propose Hierarchical Hub-based Adaptive Navigation (HHAN), an extension of AN that assigns agents only to key intersections ( hubs ). Vehicles are routed hub-to-hub under agent control, while SPF handles micro-routing within each hub region. For hub coordination, HHAN adopts centralized training with decentralized execution (CTDE) under the Attentive Q-Mixing (A-QMIX) framework, which aggregates asynchronous vehicle decisions via attention. Hub agents use flow-aware state features that combine local congestion and predictive dynamics for proactive routing. Experiments on synthetic grids and real urban maps (Toronto, Manhattan) show that AN reduces average travel time versus SPF and learning baselines, maintaining 100% routing success. HHAN scales to networks with hundreds of intersections, achieving up to 15.9% improvement under heavy traffic. These findings underscore the power of network-constrained MARL for scalable, coordinated, congestion-aware routing in intelligent transportation systems.
- 24 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 12 (4) , 1-38
Open AccessNetwork-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
Traffic congestion in urban road networks is marked by longer trip times and higher emissions, especially during peak periods. While the Shortest Path First (SPF) algorithm is optimal for a single vehicle in a static network, it performs poorly in dynamic, multi-vehicle settings, often worsening congestion by routing all vehicles along identical paths. We address dynamic vehicle routing through a multi-agent reinforcement learning (MARL) framework for coordinated, network-aware fleet navigation. We first propose Adaptive Navigation (AN), a decentralized MARL model where each intersection agent provides routing guidance based on (i) local traffic and (ii) neighborhood state modeled using Graph Attention Networks (GAT). To improve scalability in large networks, we further propose Hierarchical Hub-based Adaptive Navigation (HHAN), an extension of AN that assigns agents only to key intersections ( hubs ). Vehicles are routed hub-to-hub under agent control, while SPF handles micro-routing within each hub region. For hub coordination, HHAN adopts centralized training with decentralized execution (CTDE) under the Attentive Q-Mixing (A-QMIX) framework, which aggregates asynchronous vehicle decisions via attention. Hub agents use flow-aware state features that combine local congestion and predictive dynamics for proactive routing. Experiments on synthetic grids and real urban maps (Toronto, Manhattan) show that AN reduces average travel time versus SPF and learning baselines, maintaining 100% routing success. HHAN scales to networks with hundreds of intersections, achieving up to 15.9% improvement under heavy traffic. These findings underscore the power of network-constrained MARL for scalable, coordinated, congestion-aware routing in intelligent transportation systems.
- Open Access
- 25 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 12 (2) , 1-37
PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning
Advances in tracking technologies have spurred the rapid growth of large-scale trajectory data. Building a compact collection of pathlets, referred to as a trajectory pathlet dictionary , is essential for supporting mobility-related applications. Existing methods typically adopt a top-down approach, generating numerous candidate pathlets and selecting a subset, leading to high memory usage and redundant storage from overlapping pathlets. To overcome these limitations, we propose a bottom-up strategy that incrementally merges basic pathlets to build the dictionary, reducing memory requirements by up to 24,000 times compared to baseline methods. The approach begins with unit-length pathlets and iteratively merges them while optimizing utility, which is defined using newly introduced metrics of trajectory loss and representability . We develop a deep reinforcement learning framework, PathletRL , which utilizes Deep Q-Networks ( DQN ) to approximate the utility function, resulting in a compact and efficient pathlet dictionary. Experiments on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art techniques, reducing the size of the constructed dictionary by up to 65.8%. Additionally, our results show that only half of the dictionary pathlets are needed to reconstruct 85% of the original trajectory data. Building on PathletRL , we introduce PathletRL++ , which extends the original model by incorporating a richer state representation and an improved reward function to optimize decision-making during pathlet merging. These enhancements enable the agent to gain a more nuanced understanding of the environment, leading to higher-quality pathlet dictionaries. PathletRL++ achieves even greater dictionary size reduction, surpassing the performance of PathletRL , while maintaining high trajectory representability.
- 25 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 12 (2) , 1-37
Open AccessPathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning
Advances in tracking technologies have spurred the rapid growth of large-scale trajectory data. Building a compact collection of pathlets, referred to as a trajectory pathlet dictionary , is essential for supporting mobility-related applications. Existing methods typically adopt a top-down approach, generating numerous candidate pathlets and selecting a subset, leading to high memory usage and redundant storage from overlapping pathlets. To overcome these limitations, we propose a bottom-up strategy that incrementally merges basic pathlets to build the dictionary, reducing memory requirements by up to 24,000 times compared to baseline methods. The approach begins with unit-length pathlets and iteratively merges them while optimizing utility, which is defined using newly introduced metrics of trajectory loss and representability . We develop a deep reinforcement learning framework, PathletRL , which utilizes Deep Q-Networks ( DQN ) to approximate the utility function, resulting in a compact and efficient pathlet dictionary. Experiments on both synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art techniques, reducing the size of the constructed dictionary by up to 65.8%. Additionally, our results show that only half of the dictionary pathlets are needed to reconstruct 85% of the original trajectory data. Building on PathletRL , we introduce PathletRL++ , which extends the original model by incorporating a richer state representation and an improved reward function to optimize decision-making during pathlet merging. These enhancements enable the agent to gain a more nuanced understanding of the environment, leading to higher-quality pathlet dictionaries. PathletRL++ achieves even greater dictionary size reduction, surpassing the performance of PathletRL , while maintaining high trajectory representability.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 790-794
A Vision for Structured Experiential Mobility Intelligence
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 790-794
Open AccessA Vision for Structured Experiential Mobility Intelligence
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1306-1307
Generative Trajectory Forecasting via Transformers: The TrajLearn Framework
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1306-1307
Open AccessGenerative Trajectory Forecasting via Transformers: The TrajLearn Framework
- Open Access
Network-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
Traffic congestion in urban road networks leads to longer trip times and higher emissions, especially during peak periods. While the Shortest Path First (SPF) algorithm is optimal for a single vehicle in a static network, it performs poorly in dynamic, multi-vehicle settings, often worsening congestion by routing all vehicles along identical paths. We address dynamic vehicle routing through a multi-agent reinforcement learning (MARL) framework for coordinated, network-aware fleet navigation. We first propose Adaptive Navigation (AN), a decentralized MARL model where each intersection agent provides routing guidance based on (i) local traffic and (ii) neighborhood state modeled using Graph Attention Networks (GAT). To improve scalability in large networks, we further propose Hierarchical Hub-based Adaptive Navigation (HHAN), an extension of AN that assigns agents only to key intersections (hubs). Vehicles are routed hub-to-hub under agent control, while SPF handles micro-routing within each hub region. For hub coordination, HHAN adopts centralized training with decentralized execution (CTDE) under the Attentive Q-Mixing (A-QMIX) framework, which aggregates asynchronous vehicle decisions via attention. Hub agents use flow-aware state features that combine local congestion and predictive dynamics for proactive routing. Experiments on synthetic grids and real urban maps (Toronto, Manhattan) show that AN reduces average travel time versus SPF and learning baselines, maintaining 100% routing success. HHAN scales to networks with hundreds of intersections, achieving up to 15.9% improvement under heavy traffic. These findings highlight the potential of network-constrained MARL for scalable, coordinated, and congestion-aware routing in intelligent transportation systems.
Open AccessNetwork-Constrained Policy Optimization for Adaptive Multi-agent Vehicle Routing
Traffic congestion in urban road networks leads to longer trip times and higher emissions, especially during peak periods. While the Shortest Path First (SPF) algorithm is optimal for a single vehicle in a static network, it performs poorly in dynamic, multi-vehicle settings, often worsening congestion by routing all vehicles along identical paths. We address dynamic vehicle routing through a multi-agent reinforcement learning (MARL) framework for coordinated, network-aware fleet navigation. We first propose Adaptive Navigation (AN), a decentralized MARL model where each intersection agent provides routing guidance based on (i) local traffic and (ii) neighborhood state modeled using Graph Attention Networks (GAT). To improve scalability in large networks, we further propose Hierarchical Hub-based Adaptive Navigation (HHAN), an extension of AN that assigns agents only to key intersections (hubs). Vehicles are routed hub-to-hub under agent control, while SPF handles micro-routing within each hub region. For hub coordination, HHAN adopts centralized training with decentralized execution (CTDE) under the Attentive Q-Mixing (A-QMIX) framework, which aggregates asynchronous vehicle decisions via attention. Hub agents use flow-aware state features that combine local congestion and predictive dynamics for proactive routing. Experiments on synthetic grids and real urban maps (Toronto, Manhattan) show that AN reduces average travel time versus SPF and learning baselines, maintaining 100% routing success. HHAN scales to networks with hundreds of intersections, achieving up to 15.9% improvement under heavy traffic. These findings highlight the potential of network-constrained MARL for scalable, coordinated, and congestion-aware routing in intelligent transportation systems.
- Open Access
TraceHiding: Scalable Machine Unlearning for Mobility Data
This work introduces TraceHiding, a scalable, importance-aware machine unlearning framework for mobility trajectory data. Motivated by privacy regulations such as GDPR and CCPA granting users "the right to be forgotten," TraceHiding removes specified user trajectories from trained deep models without full retraining. It combines a hierarchical data-driven importance scoring scheme with teacher-student distillation. Importance scores--computed at token, trajectory, and user levels from statistical properties (coverage diversity, entropy, length)--quantify each training sample's impact, enabling targeted forgetting of high-impact data while preserving common patterns. The student model retains knowledge on remaining data and unlearns targeted trajectories through an importance-weighted loss that amplifies forgetting signals for unique samples and attenuates them for frequent ones. We validate on Trajectory--User Linking (TUL) tasks across three real-world higher-order mobility datasets (HO-Rome, HO-Geolife, HO-NYC) and multiple architectures (GRU, LSTM, BERT, ModernBERT, GCN-TULHOR), against strong unlearning baselines including SCRUB, NegGrad, NegGrad+, Bad-T, and Finetuning. Experiments under uniform and targeted user deletion show TraceHiding, especially its entropy-based variant, achieves superior unlearning accuracy, competitive membership inference attack (MIA) resilience, and up to 40\times speedup over retraining with minimal test accuracy loss. Results highlight robustness to adversarial deletion of high-information users and consistent performance across models. To our knowledge, this is the first systematic study of machine unlearning for trajectory data, providing a reproducible pipeline with public code and preprocessing tools.
Open AccessTraceHiding: Scalable Machine Unlearning for Mobility Data
This work introduces TraceHiding, a scalable, importance-aware machine unlearning framework for mobility trajectory data. Motivated by privacy regulations such as GDPR and CCPA granting users "the right to be forgotten," TraceHiding removes specified user trajectories from trained deep models without full retraining. It combines a hierarchical data-driven importance scoring scheme with teacher-student distillation. Importance scores--computed at token, trajectory, and user levels from statistical properties (coverage diversity, entropy, length)--quantify each training sample's impact, enabling targeted forgetting of high-impact data while preserving common patterns. The student model retains knowledge on remaining data and unlearns targeted trajectories through an importance-weighted loss that amplifies forgetting signals for unique samples and attenuates them for frequent ones. We validate on Trajectory--User Linking (TUL) tasks across three real-world higher-order mobility datasets (HO-Rome, HO-Geolife, HO-NYC) and multiple architectures (GRU, LSTM, BERT, ModernBERT, GCN-TULHOR), against strong unlearning baselines including SCRUB, NegGrad, NegGrad+, Bad-T, and Finetuning. Experiments under uniform and targeted user deletion show TraceHiding, especially its entropy-based variant, achieves superior unlearning accuracy, competitive membership inference attack (MIA) resilience, and up to 40\times speedup over retraining with minimal test accuracy loss. Results highlight robustness to adversarial deletion of high-information users and consistent performance across models. To our knowledge, this is the first systematic study of machine unlearning for trajectory data, providing a reproducible pipeline with public code and preprocessing tools.
- Open Access
- 29 July 2025
- Published by Oxford University Press (OUP) in Health Affairs Scholar
- Vol. 3 (8) , qxaf151
A policy roadmap for sustainable mass-testing
Population-wide mass testing with affordable self-tests can drastically reduce lives lost and minimize economic and societal costs during pandemics, especially if deployed before vaccines. During COVID-19, however, the development of self-test manufacturing and distribution capacity lagged behind vaccine rollout and was dismantled once surges subsided, returning us to a pre-pandemic state. As no new capacity has since been secured, future mass testing would again face costly delays. To mitigate this risk, we propose a policy roadmap for an economically viable mass-testing system that can be sustained between crises and rapidly scaled during emergencies. Public investment in R&D to improve the sensitivity of affordable self-tests—not to achieve a single benchmark, but to advance point-of-need (PoN) technologies across medical and non-medical applications—is essential. Improved sensitivity would enable new uses in routine health screening, food safety, and environmental monitoring, generating steady demand and production capacity that can expand as needed. This demand would support a robust system anchored by four mutually reinforcing pillars: scalable manufacturing, real-time data infrastructure, predictive analytics, and sustainable financing. Prioritizing sensitivity can transform mass testing from a reactive measure into a durable public health foundation.
- 29 July 2025
- Published by Oxford University Press (OUP) in Health Affairs Scholar
- Vol. 3 (8) , qxaf151
Open AccessA policy roadmap for sustainable mass-testing
Population-wide mass testing with affordable self-tests can drastically reduce lives lost and minimize economic and societal costs during pandemics, especially if deployed before vaccines. During COVID-19, however, the development of self-test manufacturing and distribution capacity lagged behind vaccine rollout and was dismantled once surges subsided, returning us to a pre-pandemic state. As no new capacity has since been secured, future mass testing would again face costly delays. To mitigate this risk, we propose a policy roadmap for an economically viable mass-testing system that can be sustained between crises and rapidly scaled during emergencies. Public investment in R&D to improve the sensitivity of affordable self-tests—not to achieve a single benchmark, but to advance point-of-need (PoN) technologies across medical and non-medical applications—is essential. Improved sensitivity would enable new uses in routine health screening, food safety, and environmental monitoring, generating steady demand and production capacity that can expand as needed. This demand would support a robust system anchored by four mutually reinforcing pillars: scalable manufacturing, real-time data infrastructure, predictive analytics, and sustainable financing. Prioritizing sensitivity can transform mass testing from a reactive measure into a durable public health foundation.
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 215-218
Demo of LearnedWMP: Workload Memory Prediction Using Deep Query Template Representations
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 215-218
Open AccessDemo of LearnedWMP: Workload Memory Prediction Using Deep Query Template Representations
- Open Access
- 7 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 11 (3) , 1-33
TrajLearn: Trajectory Prediction Learning using Deep Generative Models
Trajectory prediction aims to estimate an entity’s future path using its current position and historical movement data, benefiting fields like autonomous navigation, robotics, and human movement analytics. Deep learning approaches have become key in this area, utilizing large-scale trajectory datasets to model movement patterns, but face challenges in managing complex spatial dependencies and adapting to dynamic environments. To address these challenges, we introduce TrajLearn , a novel model for trajectory prediction that leverages generative modeling of higher-order mobility flows based on hexagonal spatial representation. TrajLearn predicts the next k steps by integrating a customized beam search for exploring multiple potential paths while maintaining spatial continuity. We conducted a rigorous evaluation of TrajLearn , benchmarking it against leading state-of-the-art approaches and meaningful baselines. The results indicate that TrajLearn achieves significant performance gains, with improvements of up to ~40% across multiple real-world trajectory datasets. In addition, we evaluated different prediction horizons (i.e., various values of k ), conducted resolution sensitivity analysis, and performed ablation studies to assess the impact of key model components. Furthermore, we developed a novel algorithm to generate mixed-resolution maps by hierarchically subdividing hexagonal regions into finer segments within a specified observation area. This approach supports selective detailing , applying finer resolution to areas of interest or high activity (e.g., urban centers) while using coarser resolution for less significant regions (e.g., rural or uninhabited areas), effectively reducing data storage requirements and computational overhead. We promote reproducibility and adaptability by offering complete code, data, and detailed documentation with flexible configuration options for various applications.
- 7 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 11 (3) , 1-33
Open AccessTrajLearn: Trajectory Prediction Learning using Deep Generative Models
Trajectory prediction aims to estimate an entity’s future path using its current position and historical movement data, benefiting fields like autonomous navigation, robotics, and human movement analytics. Deep learning approaches have become key in this area, utilizing large-scale trajectory datasets to model movement patterns, but face challenges in managing complex spatial dependencies and adapting to dynamic environments. To address these challenges, we introduce TrajLearn , a novel model for trajectory prediction that leverages generative modeling of higher-order mobility flows based on hexagonal spatial representation. TrajLearn predicts the next k steps by integrating a customized beam search for exploring multiple potential paths while maintaining spatial continuity. We conducted a rigorous evaluation of TrajLearn , benchmarking it against leading state-of-the-art approaches and meaningful baselines. The results indicate that TrajLearn achieves significant performance gains, with improvements of up to ~40% across multiple real-world trajectory datasets. In addition, we evaluated different prediction horizons (i.e., various values of k ), conducted resolution sensitivity analysis, and performed ablation studies to assess the impact of key model components. Furthermore, we developed a novel algorithm to generate mixed-resolution maps by hierarchically subdividing hexagonal regions into finer segments within a specified observation area. This approach supports selective detailing , applying finer resolution to areas of interest or high activity (e.g., urban centers) while using coarser resolution for less significant regions (e.g., rural or uninhabited areas), effectively reducing data storage requirements and computational overhead. We promote reproducibility and adaptability by offering complete code, data, and detailed documentation with flexible configuration options for various applications.