@article{nokey,

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}

}

@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}

}

@article{DSAAnish,

title = {Domain-Specific Architectures (DSAs): Research Problems and Promising Approaches},

author = {Krishnakumar, Anish and Ogras, Umit Y and Marculescu, Radu and Kishinevsky, Michael and Mudge, Trevor },

url = {https://dl.acm.org/doi/full/10.1145/3563946},

year  = {2022},

date = {2022-10-07},

urldate = {2022-10-07},

journal = {ACM Transactions on Embedded Computing Systems (TECS)},

keywords = {Edge AI, Embedded Systems, Internet of Things, Systems},

pubstate = {published},

tppubtype = {article}

}

@article{esweek2021,

title = {FLASH: Fast Neural Architecture Search with Hardware Optimization},

author = {Guihong Li and Sumit K Mandal and Umit Y Ogras and Radu Marculescu},

url = {https://dl.acm.org/doi/10.1145/3476994},

year  = {2021},

date = {2021-10-12},

journal = {ACM Transactions on Embedded Computing Systems},

volume = {20},

number = {63},

pages = {1-26},

keywords = {Edge AI, Embedded Systems, Model Compression \& Optimization, Neural Architecture Search},

pubstate = {published},

tppubtype = {article}

}

@article{chen2020fedmax,

title = {FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning},

author = {Wei Chen and Kartikeya Bhardwaj and Radu Marculescu},

url = {https://arxiv.org/abs/2004.03657},

year  = {2020},

date = {2020-01-01},

journal = {The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) },

keywords = {Edge AI, Federated Learning},

pubstate = {published},

tppubtype = {article}

}

@article{bhardwaj2020new,

title = {New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design},

author = {Kartikeya Bhardwaj and Wei Chen and Radu Marculescu},

url = {https://arxiv.org/pdf/2008.10805},

year  = {2020},

date = {2020-01-01},

journal = {arXiv preprint arXiv:2008.10805},

keywords = {Edge AI, Internet of Things},

pubstate = {published},

tppubtype = {article}

}

@article{bhardwaj2019dream,

title = {Dream distillation: A data-independent model compression framework},

author = {Kartikeya Bhardwaj and Naveen Suda and Radu Marculescu},

url = {https://arxiv.org/abs/1905.07072},

year  = {2019},

date = {2019-01-01},

journal = {arXiv preprint arXiv:1905.07072},

keywords = {Edge AI, Model Compression \& Optimization},

pubstate = {published},

tppubtype = {article}

}

@article{bhardwaj2019memory,

title = {Memory-and communication-aware model compression for distributed deep learning inference on iot},

author = {Kartikeya Bhardwaj and Ching-Yi Lin and Anderson Sartor and Radu Marculescu},

url = {https://arxiv.org/abs/1907.11804},

year  = {2019},

date = {2019-01-01},

journal = {ACM Transactions on Embedded Computing Systems (TECS)},

volume = {18},

number = {5s},

pages = {1--22},

publisher = {ACM New York, NY, USA},

keywords = {Edge AI, Featured, Model Compression \& Optimization, Networks},

pubstate = {published},

tppubtype = {article}

}

@article{bhardwaj2019edgeai,

title = {EdgeAI: A Vision for Deep Learning in IoT Era},

author = {Kartikeya Bhardwaj and Naveen Suda and Radu Marculescu},

url = {https://arxiv.org/abs/1910.10356},

year  = {2019},

date = {2019-01-01},

journal = {IEEE Design \& Test},

publisher = {IEEE},

keywords = {Edge AI, Internet of Things},

pubstate = {published},

tppubtype = {article}

}