bibliography.bib

@misc{10.48550/ARXIV.1706.02216,
  doi = {10.48550/ARXIV.1706.02216},
  url = {https://arxiv.org/abs/1706.02216},
  author = {Hamilton, William L. and Ying, Rex and Leskovec, Jure},
  keywords = {Social and Information Networks (cs.SI), Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Inductive Representation Learning on Large Graphs},
  publisher = {arXiv},
  year = {2017},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1704.01212,
  doi = {10.48550/ARXIV.1704.01212},
  url = {https://arxiv.org/abs/1704.01212},
  author = {Gilmer, Justin and Schoenholz, Samuel S. and Riley, Patrick F. and Vinyals, Oriol and Dahl, George E.},
  keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences, I.2.6},
  title = {Neural Message Passing for Quantum Chemistry},
  publisher = {arXiv},
  year = {2017},
  copyright = {arXiv.org perpetual, non-exclusive license}
}



@article{DBLP:journals/corr/abs-2003-03123,
  author    = {Johannes Klicpera and
               Janek Gro{\ss} and
               Stephan G\"unnemann},
  title     = {Directional Message Passing for Molecular Graphs},
  journal   = {CoRR},
  volume    = {abs/2003.03123},
  year      = {2020},
  url       = {https://arxiv.org/abs/2003.03123},
  eprinttype = {arXiv},
  eprint    = {2003.03123},
  timestamp = {Tue, 10 Mar 2020 13:33:48 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2003-03123.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{https://doi.org/10.48550/arxiv.2106.08903,
  doi = {10.48550/ARXIV.2106.08903},
  url = {https://arxiv.org/abs/2106.08903},
  author = {Gasteiger, Johannes and Becker, Florian and G\"unnemann, Stephan},
  keywords = {Computational Physics (physics.comp-ph), Machine Learning (cs.LG), Chemical Physics (physics.chem-ph), Machine Learning (stat.ML), FOS: Physical sciences, FOS: Physical sciences, FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {GemNet: Universal Directional Graph Neural Networks for Molecules},
  publisher = {arXiv},
  year = {2021},
  copyright = {Creative Commons Attribution 4.0 International}
}

@misc{https://doi.org/10.48550/arxiv.2203.09697,
  doi = {10.48550/ARXIV.2203.09697},
  url = {https://arxiv.org/abs/2203.09697},
  author = {Sriram, Anuroop and Das, Abhishek and Wood, Brandon M. and Goyal, Siddharth and Zitnick, C. Lawrence},
  keywords = {Machine Learning (cs.LG), Computational Physics (physics.comp-ph), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Physical sciences, FOS: Physical sciences},
  title = {Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{https://doi.org/10.48550/arxiv.1910.02054,
  doi = {10.48550/ARXIV.1910.02054},
  
  url = {https://arxiv.org/abs/1910.02054},
  
  author = {Rajbhandari, Samyam and Rasley, Jeff and Ruwase, Olatunji and He, Yuxiong},
  
  keywords = {Machine Learning (cs.LG), Distributed, Parallel, and Cluster Computing (cs.DC), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {ZeRO: Memory Optimizations Toward Training Trillion Parameter Models},
  
  publisher = {arXiv},
  
  year = {2019},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1811.02084,
  doi = {10.48550/ARXIV.1811.02084},
  
  url = {https://arxiv.org/abs/1811.02084},
  
  author = {Shazeer, Noam and Cheng, Youlong and Parmar, Niki and Tran, Dustin and Vaswani, Ashish and Koanantakool, Penporn and Hawkins, Peter and Lee, HyoukJoong and Hong, Mingsheng and Young, Cliff and Sepassi, Ryan and Hechtman, Blake},
  
  keywords = {Machine Learning (cs.LG), Distributed, Parallel, and Cluster Computing (cs.DC), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Mesh-TensorFlow: Deep Learning for Supercomputers},
  
  publisher = {arXiv},
  
  year = {2018},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1909.08053,
  doi = {10.48550/ARXIV.1909.08053},
  
  url = {https://arxiv.org/abs/1909.08053},
  
  author = {Shoeybi, Mohammad and Patwary, Mostofa and Puri, Raul and LeGresley, Patrick and Casper, Jared and Catanzaro, Bryan},
  
  keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism},
  
  publisher = {arXiv},
  
  year = {2019},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1811.06965,
  doi = {10.48550/ARXIV.1811.06965},
  
  url = {https://arxiv.org/abs/1811.06965},
  
  author = {Huang, Yanping and Cheng, Youlong and Bapna, Ankur and Firat, Orhan and Chen, Mia Xu and Chen, Dehao and Lee, HyoukJoong and Ngiam, Jiquan and Le, Quoc V. and Wu, Yonghui and Chen, Zhifeng},
  
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism},
  
  publisher = {arXiv},
  
  year = {2018},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1806.03377,
  doi = {10.48550/ARXIV.1806.03377},
  
  url = {https://arxiv.org/abs/1806.03377},
  
  author = {Harlap, Aaron and Narayanan, Deepak and Phanishayee, Amar and Seshadri, Vivek and Devanur, Nikhil and Ganger, Greg and Gibbons, Phil},
  
  keywords = {Distributed, Parallel, and Cluster Computing (cs.DC), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {PipeDream: Fast and Efficient Pipeline Parallel DNN Training},
  
  publisher = {arXiv},
  
  year = {2018},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}
@misc{https://doi.org/10.48550/arxiv.1806.01261,
  doi = {10.48550/ARXIV.1806.01261},
  
  url = {https://arxiv.org/abs/1806.01261},
  
  author = {Battaglia, Peter W. and Hamrick, Jessica B. and Bapst, Victor and Sanchez-Gonzalez, Alvaro and Zambaldi, Vinicius and Malinowski, Mateusz and Tacchetti, Andrea and Raposo, David and Santoro, Adam and Faulkner, Ryan and Gulcehre, Caglar and Song, Francis and Ballard, Andrew and Gilmer, Justin and Dahl, George and Vaswani, Ashish and Allen, Kelsey and Nash, Charles and Langston, Victoria and Dyer, Chris and Heess, Nicolas and Wierstra, Daan and Kohli, Pushmeet and Botvinick, Matt and Vinyals, Oriol and Li, Yujia and Pascanu, Razvan},
  
  keywords = {Machine Learning (cs.LG), Artificial Intelligence (cs.AI), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Relational inductive biases, deep learning, and graph networks},
  
  publisher = {arXiv},
  
  year = {2018},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@article{Chanussot_2021,
	doi = {10.1021/acscatal.0c04525},
  
	url = {https://doi.org/10.1021%2Facscatal.0c04525},
  
	year = 2021,
	month = {may},
  
	publisher = {American Chemical Society ({ACS})},
  
	volume = {11},
  
	number = {10},
  
	pages = {6059--6072},
  
	author = {Lowik Chanussot and Abhishek Das and Siddharth Goyal and Thibaut Lavril and Muhammed Shuaibi and Morgane Riviere and Kevin Tran and Javier Heras-Domingo and Caleb Ho and Weihua Hu and Aini Palizhati and Anuroop Sriram and Brandon Wood and Junwoong Yoon and Devi Parikh and C. Lawrence Zitnick and Zachary Ulissi},
  
	title = {Open Catalyst 2020 ({OC}20) Dataset and Community Challenges},
  
	journal = {{ACS} Catalysis}
}

@article{doi:10.1021/ed5004788,
author = {Baseden, Kyle A. and Tye, Jesse W.},
title = {Introduction to Density Functional Theory: Calculations by Hand on the Helium Atom},
journal = {Journal of Chemical Education},
volume = {91},
number = {12},
pages = {2116-2123},
year = {2014},
doi = {10.1021/ed5004788},

URL = { 
        https://doi.org/10.1021/ed5004788
    
},
eprint = { 
        https://doi.org/10.1021/ed5004788
    
}

}

@misc{https://doi.org/10.48550/arxiv.2206.08917,
  doi = {10.48550/ARXIV.2206.08917},
  url = {https://arxiv.org/abs/2206.08917},
  author = {Tran, Richard and Lan, Janice and Shuaibi, Muhammed and Goyal, Siddharth and Wood, Brandon M. and Das, Abhishek and Heras-Domingo, Javier and Kolluru, Adeesh and Rizvi, Ammar and Shoghi, Nima and Sriram, Anuroop and Ulissi, Zachary and Zitnick, C. Lawrence},
  keywords = {Materials Science (cond-mat.mtrl-sci), Machine Learning (cs.LG), Computational Physics (physics.comp-ph), FOS: Physical sciences, FOS: Physical sciences, FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysis},
  publisher = {arXiv},
  year = {2022},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{https://doi.org/10.48550/arxiv.2011.14115,
  doi = {10.48550/ARXIV.2011.14115},
  url = {https://arxiv.org/abs/2011.14115},
  author = {Gasteiger, Johannes and Giri, Shankari and Margraf, Johannes T. and Günnemann, Stephan},
  keywords = {Machine Learning (cs.LG), Chemical Physics (physics.chem-ph), Computational Physics (physics.comp-ph), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Physical sciences, FOS: Physical sciences},
  title = {Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules},
  publisher = {arXiv},
  year = {2020},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1710.10903,
  doi = {10.48550/ARXIV.1710.10903},
  
  url = {https://arxiv.org/abs/1710.10903},
  
  author = {Velickovic, Petar and Cucurull, Guillem and Casanova, Arantxa and Romero, Adriana and Lio, Pietro and Bengio, Yoshua},
  
  keywords = {Machine Learning (stat.ML), Artificial Intelligence (cs.AI), Machine Learning (cs.LG), Social and Information Networks (cs.SI), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Graph Attention Networks},
  
  publisher = {arXiv},
  
  year = {2017},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1903.02428,
  doi = {10.48550/ARXIV.1903.02428},
  
  url = {https://arxiv.org/abs/1903.02428},
  
  author = {Fey, Matthias and Lenssen, Jan Eric},
  
  keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Fast Graph Representation Learning with PyTorch Geometric},
  
  publisher = {arXiv},
  
  year = {2019},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@misc{10.48550/ARXIV.1909.01315,
  doi = {10.48550/ARXIV.1909.01315},
  
  url = {https://arxiv.org/abs/1909.01315},
  
  author = {Wang, Minjie and Zheng, Da and Ye, Zihao and Gan, Quan and Li, Mufei and Song, Xiang and Zhou, Jinjing and Ma, Chao and Yu, Lingfan and Gai, Yu and Xiao, Tianjun and He, Tong and Karypis, George and Li, Jinyang and Zhang, Zheng},
  
  keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks},
  
  publisher = {arXiv},
  
  year = {2019},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@article{DBLP:journals/corr/abs-2101-06840,
  author    = {Jie Ren and
               Samyam Rajbhandari and
               Reza Yazdani Aminabadi and
               Olatunji Ruwase and
               Shuangyan Yang and
               Minjia Zhang and
               Dong Li and
               Yuxiong He},
  title     = {ZeRO-Offload: Democratizing Billion-Scale Model Training},
  journal   = {CoRR},
  volume    = {abs/2101.06840},
  year      = {2021},
  url       = {https://arxiv.org/abs/2101.06840},
  eprinttype = {arXiv},
  eprint    = {2101.06840},
  timestamp = {Mon, 03 May 2021 16:42:27 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2101-06840.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2104-07857,
  author    = {Samyam Rajbhandari and
               Olatunji Ruwase and
               Jeff Rasley and
               Shaden Smith and
               Yuxiong He},
  title     = {ZeRO-Infinity: Breaking the {GPU} Memory Wall for Extreme Scale Deep
               Learning},
  journal   = {CoRR},
  volume    = {abs/2104.07857},
  year      = {2021},
  url       = {https://arxiv.org/abs/2104.07857},
  eprinttype = {arXiv},
  eprint    = {2104.07857},
  timestamp = {Mon, 19 Apr 2021 16:45:47 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2104-07857.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{ott2019fairseq,
  title = {fairseq: A Fast, Extensible Toolkit for Sequence Modeling},
  author = {Myle Ott and Sergey Edunov and Alexei Baevski and Angela Fan and Sam Gross and Nathan Ng and David Grangier and Michael Auli},
  booktitle = {Proceedings of NAACL-HLT 2019: Demonstrations},
  year = {2019},
}

@Misc{FairScale2021,
  author =       {Mandeep Baines and Shruti Bhosale and Vittorio Caggiano and Naman Goyal and Siddharth Goyal and Myle Ott and Benjamin Lefaudeux and Vitaliy Liptchinsky and Mike Rabbat and Sam Sheiffer and Anjali Sridhar and Min Xu},
  title =        {FairScale:  A general purpose modular PyTorch library for high performance and large scale training},
  howpublished = {\url{https://github.com/facebookresearch/fairscale}},
  year =         {2021}
}

@misc{https://doi.org/10.48550/arxiv.2204.02782,
  doi = {10.48550/ARXIV.2204.02782},
  url = {https://arxiv.org/abs/2204.02782},
  author = {Gasteiger, Johannes and Shuaibi, Muhammed and Sriram, Anuroop and Günnemann, Stephan and Ulissi, Zachary and Zitnick, C. Lawrence and Das, Abhishek},
  keywords = {Machine Learning (cs.LG), Materials Science (cond-mat.mtrl-sci), Chemical Physics (physics.chem-ph), Computational Physics (physics.comp-ph), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Physical sciences, FOS: Physical sciences},
  title = {How Do Graph Networks Generalize to Large and Diverse Molecular Systems?},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}