2026
10.
Munir, Mustafa; Rahman, Md Mostafijur; Marculescu, Radu
AdaptViG: Adaptive Vision GNN with Exponential Decay Gating Conference Forthcoming
2026 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026), Forthcoming.
Links | BibTeX | Tags: Deep Learning, Deep Learning Architecture, Efficient AI, Featured, Graph Neural Network
@conference{AdaptViG_WACV_2026,
title = {AdaptViG: Adaptive Vision GNN with Exponential Decay Gating},
author = {Mustafa Munir and Md Mostafijur Rahman and Radu Marculescu},
url = {https://arxiv.org/abs/2511.09942},
year = {2026},
date = {2026-03-02},
booktitle = {2026 Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026)},
keywords = {Deep Learning, Deep Learning Architecture, Efficient AI, Featured, Graph Neural Network},
pubstate = {forthcoming},
tppubtype = {conference}
}
2025
9.
Munir, Mustafa; Rahman, Md Mostafijur; Wei, Xiwen; Yang, Yuedong; Marculescu, Radu
SearchViG: Optimal Vision GNNs via Ramanujan Spectral Optimization Conference Forthcoming
The Fourth Learning on Graphs Conference (LOG 2025), Forthcoming.
Links | BibTeX | Tags: Deep Learning, Deep Learning Architecture, Dynamic networks, Efficient AI, Featured, Graph Neural Network
@conference{SearchViG_LOG_2025,
title = {SearchViG: Optimal Vision GNNs via Ramanujan Spectral Optimization},
author = {Mustafa Munir and Md Mostafijur Rahman and Xiwen Wei and Yuedong Yang and Radu Marculescu},
url = {https://openreview.net/pdf?id=cmEzgaYIJC},
year = {2025},
date = {2025-12-15},
booktitle = {The Fourth Learning on Graphs Conference (LOG 2025)},
keywords = {Deep Learning, Deep Learning Architecture, Dynamic networks, Efficient AI, Featured, Graph Neural Network},
pubstate = {forthcoming},
tppubtype = {conference}
}
8.
Gedik, Hakan Emre; Martin, Andrew; Munir, Mustafa; Baser, Oguzhan; Marculescu, Radu; Chinchali, Sandeep P.; Bovik, Alan C.
AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs Technical Report
2025.
Links | BibTeX | Tags: Deep Learning, Deep Learning Architecture, Efficient AI, Graph Neural Network
@techreport{AttentionViG,
title = {AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs},
author = {Hakan Emre Gedik and Andrew Martin and Mustafa Munir and Oguzhan Baser and Radu Marculescu and Sandeep P. Chinchali and Alan C. Bovik},
url = {https://www.arxiv.org/abs/2509.25570},
year = {2025},
date = {2025-09-29},
keywords = {Deep Learning, Deep Learning Architecture, Efficient AI, Graph Neural Network},
pubstate = {published},
tppubtype = {techreport}
}
7.
Hurtado, Sofia; Marculescu, Radu
Graph Learning for Bidirectional Disease Contact Tracing on Real Human Mobility Data Workshop
Advances in Social Networks Analysis and Mining, Springer, 2025, ISBN: 978-3-031-85386-9, (Article presented at the REINFORCE workshop in the ASONAM conference in September 2024, and finally published in June 2025).
Abstract | Links | BibTeX | Tags: Disease Mitigation, Graph Neural Network, Human Mobility Data
@workshop{Hurtado2024,
title = {Graph Learning for Bidirectional Disease Contact Tracing on Real Human Mobility Data},
author = {Sofia Hurtado and Radu Marculescu },
editor = {I-Hsien Ting and Reda Alhajj and Panagiotis Karampelas and Min-Yuh Day},
url = {https://link.springer.com/book/9783031785535},
doi = {10.1007/978-3-031-85386-9_15},
isbn = {978-3-031-85386-9},
year = {2025},
date = {2025-06-11},
urldate = {2025-06-11},
booktitle = {Advances in Social Networks Analysis and Mining},
issue = {ASONAM},
publisher = {Springer},
abstract = {For rapidly spreading diseases where many cases show no symptoms, swift and effective contact tracing is essential. While exposure notification applications provide alerts on potential exposures, a fully automated system is needed to track the infectious transmission routes. To this end, our research leverages large-scale contact networks from real human mobility data to identify the path of transmission. More precisely, we introduce a new Infectious Path Centrality network metric that informs a graph learning edge classifier to identify important trans- mission events, achieving an F1-score of 94%. Additionally, we explore bidirectional contact tracing, which quarantines individuals both retroactively and proactively, and compare its effectiveness against traditional forward tracing, which only isolates individuals after testing positive. Our results indicate that when only 30% of symptomatic individuals are tested, bidirectional tracing can reduce infectious effective reproduction rate by 71%, thus significantly controlling the outbreak.},
howpublished = {Social Networks Analysis and Mining},
note = {Article presented at the REINFORCE workshop in the ASONAM conference in September 2024, and finally published in June 2025},
keywords = {Disease Mitigation, Graph Neural Network, Human Mobility Data},
pubstate = {published},
tppubtype = {workshop}
}
For rapidly spreading diseases where many cases show no symptoms, swift and effective contact tracing is essential. While exposure notification applications provide alerts on potential exposures, a fully automated system is needed to track the infectious transmission routes. To this end, our research leverages large-scale contact networks from real human mobility data to identify the path of transmission. More precisely, we introduce a new Infectious Path Centrality network metric that informs a graph learning edge classifier to identify important trans- mission events, achieving an F1-score of 94%. Additionally, we explore bidirectional contact tracing, which quarantines individuals both retroactively and proactively, and compare its effectiveness against traditional forward tracing, which only isolates individuals after testing positive. Our results indicate that when only 30% of symptomatic individuals are tested, bidirectional tracing can reduce infectious effective reproduction rate by 71%, thus significantly controlling the outbreak.
2024
6.
Munir, Mustafa; Zhang, Alex; Marculescu, Radu
Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs Conference
The Third Learning on Graphs Conference (LOG 2024), 2024.
Links | BibTeX | Tags: Deep Learning Architecture, Edge AI, Graph Neural Network
@conference{LogViG_LOG_2024,
title = {Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs},
author = {Mustafa Munir and Alex Zhang and Radu Marculescu},
url = {https://github.com/mmunir127/LogViG-Official},
year = {2024},
date = {2024-11-26},
urldate = {2024-11-26},
booktitle = {The Third Learning on Graphs Conference (LOG 2024)},
keywords = {Deep Learning Architecture, Edge AI, Graph Neural Network},
pubstate = {published},
tppubtype = {conference}
}
5.
Munir, Mustafa; Avery, William; Rahman, Md Mostafijur; Marculescu, Radu
GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs Conference
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Abstract | Links | BibTeX | Tags: Deep Learning Architecture, Dynamic networks, Edge AI, Efficient Inference, Graph Neural Network
@conference{GreedyViG_CVPR_2024,
title = {GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs},
author = {Mustafa Munir and William Avery and Md Mostafijur Rahman and Radu Marculescu},
url = {https://openaccess.thecvf.com/content/CVPR2024/papers/Munir_GreedyViG_Dynamic_Axial_Graph_Construction_for_Efficient_Vision_GNNs_CVPR_2024_paper.pdf},
year = {2024},
date = {2024-06-19},
urldate = {2024-06-19},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
abstract = {Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNNGNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models.},
keywords = {Deep Learning Architecture, Dynamic networks, Edge AI, Efficient Inference, Graph Neural Network},
pubstate = {published},
tppubtype = {conference}
}
Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN as it limits the number of considered graph connections made within an image. Additionally, we propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC. Extensive experiments show that GreedyViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification, object detection, instance segmentation, and semantic segmentation tasks. Our smallest model, GreedyViG-S, achieves 81.1% top-1 accuracy on ImageNet-1K, 2.9% higher than Vision GNN and 2.2% higher than Vision HyperGraph Neural Network (ViHGNN), with less GMACs and a similar number of parameters. Our largest model, GreedyViG-B obtains 83.9% top-1 accuracy, 0.2% higher than Vision GNN, with a 66.6% decrease in parameters and a 69% decrease in GMACs. GreedyViG-B also obtains the same accuracy as ViHGNN with a 67.3% decrease in parameters and a 71.3% decrease in GMACs. Our work shows that hybrid CNNGNN architectures not only provide a new avenue for designing efficient models, but that they can also exceed the performance of current state-of-the-art models.
4.
Munir, Mustafa; Modi, Saloni; Cooper, Geffen; Kim, Huntae; Marculescu, Radu
Three Decades of Low Power: From Watts to Wisdom Journal Article
In: IEEE Access, vol. 12, pp. 19447-19458, 2024.
Links | BibTeX | Tags: Dynamic networks, Edge AI, Featured, Graph Neural Network
@article{10418914,
title = {Three Decades of Low Power: From Watts to Wisdom},
author = {Mustafa Munir and Saloni Modi and Geffen Cooper and Huntae Kim and Radu Marculescu},
url = {https://ieeexplore.ieee.org/document/10418914},
doi = {10.1109/ACCESS.2024.3361484},
year = {2024},
date = {2024-02-02},
urldate = {2024-02-02},
journal = {IEEE Access},
volume = {12},
pages = {19447-19458},
keywords = {Dynamic networks, Edge AI, Featured, Graph Neural Network},
pubstate = {published},
tppubtype = {article}
}
3.
Rahman, Md Mostafijur; Marculescu, Radu
G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation Conference
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024.
Links | BibTeX | Tags: Deep Learning Architecture, Graph Neural Network, Medical Image Segmentation
@conference{WACV2024Mostafij,
title = {G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation},
author = {Md Mostafijur Rahman and Radu Marculescu},
url = {https://openaccess.thecvf.com/content/WACV2024/html/Rahman_G-CASCADE_Efficient_Cascaded_Graph_Convolutional_Decoding_for_2D_Medical_Image_WACV_2024_paper.html},
year = {2024},
date = {2024-01-04},
urldate = {2024-01-04},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {7728-7737},
keywords = {Deep Learning Architecture, Graph Neural Network, Medical Image Segmentation},
pubstate = {published},
tppubtype = {conference}
}
2023
2.
Hurtado, Sofia; Marculescu, Radu
Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2023), 2023.
Abstract | Links | BibTeX | Tags: Epidemics, GPS, Graph Neural Network, Multi Agent Reinforcement Learning
@conference{Hurtado2023Q,
title = {Quarantine in Motion: A Graph Learning and Multi-Agent Reinforcement Learning Framework to Reduce Disease Transmission Without Lockdown},
author = {Sofia Hurtado and Radu Marculescu},
url = {https://ieeexplore.ieee.org/document/10068686},
year = {2023},
date = {2023-11-06},
urldate = {2023-11-06},
booktitle = {Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2023)},
abstract = {Exposure notification applications are designed to help trace disease spreading by alerting exposed individuals to get tested. However, false alarms can cause users to become hesitant to respond, making the applications ineffective. To address the shortcomings of slow manual contact tracing, costly lockdowns, and unreliable exposure notification applications, better disease mitigation strategies are needed. In this study, we propose a new disease mitigation paradigm where people can reduce infection spreading while maintaining some mobility (i.e., Quarantine in Motion). Our approach utilizes Graph Neural Networks (GNNs) to predict disease hotspots such as restaurants, shops and parks, and Multi-Agent Reinforcement Learning (MARL) to collaboratively manage human mobility to reduce disease transmission. As proof of concept, we simulate an infection using real-world mobility data from New York City (over 200,000 devices) and Austin (over 36,000 devices) and train 10,000 agents from each city to manage disease dynamics. Through simulation, we show that a trained population suppresses their reproduction rate below 1, thereby mitigating the outbreak.},
keywords = {Epidemics, GPS, Graph Neural Network, Multi Agent Reinforcement Learning},
pubstate = {published},
tppubtype = {conference}
}
Exposure notification applications are designed to help trace disease spreading by alerting exposed individuals to get tested. However, false alarms can cause users to become hesitant to respond, making the applications ineffective. To address the shortcomings of slow manual contact tracing, costly lockdowns, and unreliable exposure notification applications, better disease mitigation strategies are needed. In this study, we propose a new disease mitigation paradigm where people can reduce infection spreading while maintaining some mobility (i.e., Quarantine in Motion). Our approach utilizes Graph Neural Networks (GNNs) to predict disease hotspots such as restaurants, shops and parks, and Multi-Agent Reinforcement Learning (MARL) to collaboratively manage human mobility to reduce disease transmission. As proof of concept, we simulate an infection using real-world mobility data from New York City (over 200,000 devices) and Austin (over 36,000 devices) and train 10,000 agents from each city to manage disease dynamics. Through simulation, we show that a trained population suppresses their reproduction rate below 1, thereby mitigating the outbreak.
1.
Xue, Zihui; Yang, Yuedong; Marculescu, Radu
SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning Journal Article
In: IEEE Transactions on Computers, 2023, ISSN: 0018-9340.
Abstract | Links | BibTeX | Tags: Edge AI, Graph Neural Network
@article{nokey,
title = {SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning},
author = {Zihui Xue and Yuedong Yang and Radu Marculescu},
doi = {10.1109/TC.2023.3288755},
issn = {0018-9340},
year = {2023},
date = {2023-06-29},
urldate = {2023-06-29},
journal = {IEEE Transactions on Computers},
abstract = {Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Nevertheless, resource-efficient GNN learning is a rarely explored topic despite its many benefits for edge computing and Internet of Things (IoT) applications. To improve this state of affairs, this work proposes efficient su b g raph-level tr a ining via r esource-aware graph partitioning (SUGAR). SUGAR first partitions the initial graph into a set of disjoint subgraphs and then performs local training at the subgraph-level We provide a theoretical analysis and conduct extensive experiments on five graph benchmarks to verify its efficacy in practice. Our results across five different hardware platforms demonstrate great runtime speedup and memory reduction of SUGAR on large-scale graphs. We believe SUGAR opens a new research direction towards developing GNN methods that are resource-efficient, hence suitable for IoT deployment. Our code is publicly available at: https://github.com/zihuixue/SUGAR.},
keywords = {Edge AI, Graph Neural Network},
pubstate = {published},
tppubtype = {article}
}
Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Nevertheless, resource-efficient GNN learning is a rarely explored topic despite its many benefits for edge computing and Internet of Things (IoT) applications. To improve this state of affairs, this work proposes efficient su b g raph-level tr a ining via r esource-aware graph partitioning (SUGAR). SUGAR first partitions the initial graph into a set of disjoint subgraphs and then performs local training at the subgraph-level We provide a theoretical analysis and conduct extensive experiments on five graph benchmarks to verify its efficacy in practice. Our results across five different hardware platforms demonstrate great runtime speedup and memory reduction of SUGAR on large-scale graphs. We believe SUGAR opens a new research direction towards developing GNN methods that are resource-efficient, hence suitable for IoT deployment. Our code is publicly available at: https://github.com/zihuixue/SUGAR.
