Fandel Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fandel Lin has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Craig A. Knoblock
University of Southern California
10 shared publications - Hsun-Ping Hsieh
Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan
10 shared publications - Yao-Yi Chiang
University of Minnesota, Minneapolis, Minnesota, USA
5 shared publications - Binh Vu
Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA
4 shared publications - Basel Shbita
IBM Research, San Jose, CA, USA
3 shared publications - Pei-Xuan Li
Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan
3 shared publications
Latest Publications
- Open Access
- 27 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (3) , 1-24
Enhancing POI Recommendation through Global Graph Disentanglement with POI Weighted Module
Next Point of Interest (POI) recommendation primarily predicts future activities based on users’ past check-in data and current status, providing significant value to users and service providers. We observed that the popular check-in times for different POI categories vary. For example, coffee shops are crowded in the afternoon because people like to have coffee to refresh after meals, while bars are busy late at night. However, existing methods rarely explore the relationship between POI categories and time, which may result in the model being unable to fully learn users’ tendencies to visit certain POI categories at different times. Additionally, existing methods for modeling time information often convert it into time embeddings or calculate the time interval and incorporate it into the model, making it difficult to capture the continuity of time. Finally, during POI prediction, various weighting information is often ignored, such as the popularity of each POI, the transition relationships between POIs, and the distances between POIs, leading to suboptimal performance. To address these issues, this article proposes a novel next POI recommendation framework called Graph Disentangler with POI Weighted Module (GDPW) . This framework aims to jointly consider POI category information and multiple POI weighting factors. Specifically, the proposed GDPW learns category and time representations through the Global Category Graph and the Global Category-Time Graph. Then, we disentangle category and time information through contrastive learning. After prediction, the final POI recommendation for users is obtained by weighting the prediction results based on the transition weights and distance relationships between POIs. We conducted experiments on two real-world datasets, and the results demonstrate that the proposed GDPW outperforms other existing models, improving performance by 3% to 11%.
- 27 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 17 (3) , 1-24
Open AccessEnhancing POI Recommendation through Global Graph Disentanglement with POI Weighted Module
Next Point of Interest (POI) recommendation primarily predicts future activities based on users’ past check-in data and current status, providing significant value to users and service providers. We observed that the popular check-in times for different POI categories vary. For example, coffee shops are crowded in the afternoon because people like to have coffee to refresh after meals, while bars are busy late at night. However, existing methods rarely explore the relationship between POI categories and time, which may result in the model being unable to fully learn users’ tendencies to visit certain POI categories at different times. Additionally, existing methods for modeling time information often convert it into time embeddings or calculate the time interval and incorporate it into the model, making it difficult to capture the continuity of time. Finally, during POI prediction, various weighting information is often ignored, such as the popularity of each POI, the transition relationships between POIs, and the distances between POIs, leading to suboptimal performance. To address these issues, this article proposes a novel next POI recommendation framework called Graph Disentangler with POI Weighted Module (GDPW) . This framework aims to jointly consider POI category information and multiple POI weighting factors. Specifically, the proposed GDPW learns category and time representations through the Global Category Graph and the Global Category-Time Graph. Then, we disentangle category and time information through contrastive learning. After prediction, the final POI recommendation for users is obtained by weighting the prediction results based on the transition weights and distance relationships between POIs. We conducted experiments on two real-world datasets, and the results demonstrate that the proposed GDPW outperforms other existing models, improving performance by 3% to 11%.
- Open Access
- 3 February 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 120 (1) , 41
Predicting Origin-Destination Traffic with Advanced Spatio-Temporal Networks
Existing origin-destination (OD) forecasting models struggle to jointly capture local topology and global flow patterns in urban mobility. Therefore, we developed a multi-view spatio-temporal network (MVSTN), a novel dual-branch spatio-temporal model that integrates a graph convolutional network-based local spatial relationship module for static and dynamic graph modeling, and a self-attention-based global similarity module for learning latent mobility similarities. MVSTN achieves superior performance on multiple real-world datasets, particularly in long-term forecasts, highlighting its practical value for intelligent transportation systems.
- 3 February 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 120 (1) , 41
Open AccessPredicting Origin-Destination Traffic with Advanced Spatio-Temporal Networks
Existing origin-destination (OD) forecasting models struggle to jointly capture local topology and global flow patterns in urban mobility. Therefore, we developed a multi-view spatio-temporal network (MVSTN), a novel dual-branch spatio-temporal model that integrates a graph convolutional network-based local spatial relationship module for static and dynamic graph modeling, and a self-attention-based global similarity module for learning latent mobility similarities. MVSTN achieves superior performance on multiple real-world datasets, particularly in long-term forecasts, highlighting its practical value for intelligent transportation systems.
- Open Access
- 2 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
An Integrated Approach to Multi-agent Scheduling with Bounded Objectives in an Urban Setting
Road inspection and cleaning are crucial to securing driving safety. Deploying a fleet of robots that run through a city can inspect and clean pavements without causing road closure. To achieve high coverage, one has to prevent robots from going through a road segment more than necessary. However, robots may need more than one visit to a particular road segment to inspect a defect. The uncertain success rate of defect inspection and the unknown maximum number of defects hinder the efficacy. Such uncertainty and constraints in objectives can also be seen in security patrolling, trip planning, and network maintenance. We target the problem of multi-agent scheduling with bounded objectives. The scheduling aims for maximum road network coverage while ensuring sufficient visits to particular road segments for defect identification of an uncertain subject, such as potholes and faded markings during road inspection or crimes and parking violations during security patrolling. We leverage an approximate bi-objective algorithm and propose a hierarchical circular route-planning algorithm. Our approach maximizes the road coverage among robots and decreases the search space when maximizing defect identification. We evaluate our approach on four real-world datasets. Our approach outperforms comparative methods by 11% in multi-objective optimization.
- 2 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
Open AccessAn Integrated Approach to Multi-agent Scheduling with Bounded Objectives in an Urban Setting
Road inspection and cleaning are crucial to securing driving safety. Deploying a fleet of robots that run through a city can inspect and clean pavements without causing road closure. To achieve high coverage, one has to prevent robots from going through a road segment more than necessary. However, robots may need more than one visit to a particular road segment to inspect a defect. The uncertain success rate of defect inspection and the unknown maximum number of defects hinder the efficacy. Such uncertainty and constraints in objectives can also be seen in security patrolling, trip planning, and network maintenance. We target the problem of multi-agent scheduling with bounded objectives. The scheduling aims for maximum road network coverage while ensuring sufficient visits to particular road segments for defect identification of an uncertain subject, such as potholes and faded markings during road inspection or crimes and parking violations during security patrolling. We leverage an approximate bi-objective algorithm and propose a hierarchical circular route-planning algorithm. Our approach maximizes the road coverage among robots and decreases the search space when maximizing defect identification. We evaluate our approach on four real-world datasets. Our approach outperforms comparative methods by 11% in multi-objective optimization.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 717-728
DIGMAPPER: A Modular System for Automated Geologic Map Digitization
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 717-728
Open AccessDIGMAPPER: A Modular System for Automated Geologic Map Digitization
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1126-1129
Exploiting Polygon Metadata to Colorize Draft Maps
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1126-1129
Open AccessExploiting Polygon Metadata to Colorize Draft Maps
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1234-1237
MoVER: Modeling User Heterogeneity with Enriched Trajectory Representations for Human Mobility Prediction
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1234-1237
Open AccessMoVER: Modeling User Heterogeneity with Enriched Trajectory Representations for Human Mobility Prediction
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1122-1125
Exploiting Polygon Metadata to Recolor Historical Maps
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1122-1125
Open AccessExploiting Polygon Metadata to Recolor Historical Maps
- Open Access
Enhancing POI Recommendation through Global Graph Disentanglement with POI Weighted Module
Next point of interest (POI) recommendation primarily predicts future activities based on users' past check-in data and current status, providing significant value to users and service providers. We observed that the popular check-in times for different POI categories vary. For example, coffee shops are crowded in the afternoon because people like to have coffee to refresh after meals, while bars are busy late at night. However, existing methods rarely explore the relationship between POI categories and time, which may result in the model being unable to fully learn users' tendencies to visit certain POI categories at different times. Additionally, existing methods for modeling time information often convert it into time embeddings or calculate the time interval and incorporate it into the model, making it difficult to capture the continuity of time. Finally, during POI prediction, various weighting information is often ignored, such as the popularity of each POI, the transition relationships between POIs, and the distances between POIs, leading to suboptimal performance. To address these issues, this paper proposes a novel next POI recommendation framework called Graph Disentangler with POI Weighted Module (GDPW). This framework aims to jointly consider POI category information and multiple POI weighting factors. Specifically, the proposed GDPW learns category and time representations through the Global Category Graph and the Global Category-Time Graph. Then, we disentangle category and time information through contrastive learning. After prediction, the final POI recommendation for users is obtained by weighting the prediction results based on the transition weights and distance relationships between POIs. We conducted experiments on two real-world datasets, and the results demonstrate that the proposed GDPW outperforms other existing models, improving performance by 3% to 11%.
Open AccessEnhancing POI Recommendation through Global Graph Disentanglement with POI Weighted Module
Next point of interest (POI) recommendation primarily predicts future activities based on users' past check-in data and current status, providing significant value to users and service providers. We observed that the popular check-in times for different POI categories vary. For example, coffee shops are crowded in the afternoon because people like to have coffee to refresh after meals, while bars are busy late at night. However, existing methods rarely explore the relationship between POI categories and time, which may result in the model being unable to fully learn users' tendencies to visit certain POI categories at different times. Additionally, existing methods for modeling time information often convert it into time embeddings or calculate the time interval and incorporate it into the model, making it difficult to capture the continuity of time. Finally, during POI prediction, various weighting information is often ignored, such as the popularity of each POI, the transition relationships between POIs, and the distances between POIs, leading to suboptimal performance. To address these issues, this paper proposes a novel next POI recommendation framework called Graph Disentangler with POI Weighted Module (GDPW). This framework aims to jointly consider POI category information and multiple POI weighting factors. Specifically, the proposed GDPW learns category and time representations through the Global Category Graph and the Global Category-Time Graph. Then, we disentangle category and time information through contrastive learning. After prediction, the final POI recommendation for users is obtained by weighting the prediction results based on the transition weights and distance relationships between POIs. We conducted experiments on two real-world datasets, and the results demonstrate that the proposed GDPW outperforms other existing models, improving performance by 3% to 11%.
- 15 June 2025
- Published by Springer Nature
- p. 29-40
FOG: Interpretable Feature-Oriented Graph Neural Networks for Tabular Data Prediction
- 15 June 2025
- Published by Springer Nature
- p. 29-40
FOG: Interpretable Feature-Oriented Graph Neural Networks for Tabular Data Prediction
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1724-1732
Embedding Spatial and Semantic Contexts for Geo-Entity Typing in Smart City Applications
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1724-1732
Open AccessEmbedding Spatial and Semantic Contexts for Geo-Entity Typing in Smart City Applications