Sheikh Shams Azam bio photo

Sheikh Shams Azam

Apple  | Purdue | NITK

Email Google Scholar ResearchGate LinkedIn Github ORCID Twitter Instagram Quotes Updated: 05/2024

Pre-prints

[P1] Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan “Honza” Silovsky, Kunal Talwar, and Tatiana Likhomanenko. “Federated Learning with Differential Privacy for End-to-End Speech Recognition.” arXiv preprint arXiv:2310.00098, 2023.
[preprint]
@article{pelikan2023federated,
  title={Federated Learning with Differential Privacy for End-to-End Speech Recognition},
  author={Pelikan, Martin and Azam, Sheikh Shams and Feldman, Vitaly and Silovsky, Jan and Talwar, Kunal and Likhomanenko, Tatiana},
  journal={arXiv preprint arXiv:2310.00098},
  year={2023},
  url={https://arxiv.org/abs/2310.00098},
}

Conference

[C6] Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, and Jan “Honza” Silovsky. “Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR.” In IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2023.
[paper] [apple-ml] [preprint] [video] [poster] [slides]
@inproceedings{azam2023importance,
  title={Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASR},
  author={Sheikh Shams Azam and Tatiana Likhomanenko and Martin Pelikan and Jan Silovsky},
  booktitle={IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
  year={2023},
  url={https://arxiv.org/abs/2309.13102},
}
[C5] Zeyu Zhou, Sheikh Shams Azam, Christopher G. Brinton, and David I. Inouye. “Efficient Federated Domain Translation.” In International Conference on Learning Representations (ICLR), 2023.
[paper]
@inproceedings{zhou2023fedinb,
  title     = {Efficient Federated Domain Translation},
  author    = {Zhou, Zeyu and Azam, Sheikh Shams and Brinton, Christopher G. and Inouye, David I.},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2023},
  url       = {https://openreview.net/forum?id=uhLAcrAZ9cJ}
}
[C4] Sheikh Shams Azam, Seyyedali Hosseinalipour, Qiang Qiu, and Christopher G. Brinton. “Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?” In International Conference on Learning Representations (ICLR), 2022.
[paper] [preprint] [video] [poster] [slides] [code]
@inproceedings{azam2022lbgm,
  title     = {Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?},
  author    = {Azam, Sheikh Shams and Hosseinalipour, Seyyedali and Qiu, Qiang and Brinton, Christopher G.},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2022},
  url       = {https://openreview.net/forum?id=B7ZbqNLDn-_}
}
[C3] Sheikh Shams Azam, Taejin Kim, Seyyedali Hosseinalipour, Christopher G. Brinton, Carlee Joe-Wong, and Saurabh Bagchi. “Can we Generalize and Distribute Private Representation Learning?” In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
[paper] [preprint] [video] [poster] [slides] [code]
@inproceedings{azam2022eigan,
  title     = {Can we Generalize and Distribute Private Representation Learning?},
  author    = {Azam, Sheikh Shams and Kim, Taejin and Hosseinalipour, Seyyedali and Joe-Wong, Carlee and Bagchi, Saurabh and Brinton, Christopher G.},
  booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year      = {2022},
  series    = {Proceedings of Machine Learning Research},
  volume    = {151},
  pages     = {11320--11340},
  month     = {28--30 Mar},
  publisher = {PMLR},
  url       = {https://proceedings.mlr.press/v151/shams-azam22a.html}
}
[C2] Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolò Michelusi. “Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling.” In IEEE Global Communications Conference (GLOBECOM), 2021.
[paper] [preprint] [slides] [code]
@inproceedings{lin2021flbeyondstar,
  title     = {Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling}, 
  author    = {Lin, Frank Po-Chen and Hosseinalipour, Seyyedali and Azam, Sheikh Shams and Brinton, Christopher G. and Michelusi, Nicolò},
  booktitle = {2021 IEEE Global Communications Conference (GLOBECOM)}, 
  year      = {2021},
  pages     = {1--6},
  url       = {https://ieeexplore.ieee.org/document/9685456}
}
[C1] Sheikh Shams Azam, Manoj Raju, Venkatesh Pagidimarri, and Vamsi Chandra Kasivajjala. “CASCADENET: An LSTM Based Deep Learning Model for Automated ICD-10 Coding.” In Future of Information and Communication Conference (FICC), 2019.
[paper] [preprint] [slides]
@inproceedings{azam2020cascadenet,
  title     = {CASCADENET: An LSTM Based Deep Learning Model for Automated ICD-10 Coding},
  author    = {Azam, Sheikh Shams and Raju, Manoj and Pagidimarri, Venkatesh and Kasivajjala, Vamsi Chandra},
  booktitle = {Advances in Information and Communication},
  year      = {2020},
  pages     = {55--74},
  publisher = {Springer International Publishing},
  url       = {https://link.springer.com/chapter/10.1007/978-3-030-12385-7_6}
}

Journal

[J3] Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolò Michelusi, Vaneet Aggarwal, David J. Love, and Huaiyu Dai. “Multi-Stage Hybrid Federated Learning over Large-Scale Wireless Fog Networks.” IEEE/ACM Transactions on Networking (TON), 2020.
[paper] [preprint] [code]
@article{hosseinalipour2022multistagefl,  
  title   = {Multi-Stage Hybrid Federated Learning Over Large-Scale D2D-Enabled Fog Networks},   
  author  = {Hosseinalipour, Seyyedali and Azam, Sheikh Shams and Brinton, Christopher G. and Michelusi, Nicolò and Aggarwal, Vaneet and Love, David J. and Dai, Huaiyu},  
  journal = {IEEE/ACM Transactions on Networking (TON)},   
  year    = {2022},  
  volume  = {30},  
  number  = {4},  
  pages   = {1569-1584},  
  url     = {https://ieeexplore.ieee.org/document/9705093}
}
[J2] Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, and Nicolò Michelusi. “Semi-decentralized federated learning with cooperative D2D local model aggregations.” IEEE Journal on Selected Areas in Communications (JSAC) (2021).
[paper] [preprint] [code]
@article{lin2021semidecentralizedfl,
  title   = {Semi-Decentralized Federated Learning With Cooperative D2D Local Model Aggregations}, 
  author  = {Lin, Frank Po-Chen and Hosseinalipour, Seyyedali and Azam, Sheikh Shams and Brinton, Christopher G. and Michelusi, Nicolò},
  journal = {IEEE Journal on Selected Areas in Communications (JSAC)}, 
  year    = {2021},
  volume  = {39},
  number  = {12},
  pages   = {3851--3869},
  url     = {https://ieeexplore.ieee.org/abstract/document/9562522}
}
[J1] Sheikh Shams Azam, Manoj Raju, Venkatesh Pagidimarri, and Vamsi Chandra Kasivajjala. “Q-Map: Clinical Concept Mining from Clinical Documents.” World Academy of Science, Engineering and Technology, International Journal of Computer and Information Engineering (2018).
[paper] [preprint] [slides]
@article{azam2018qmap,
  title     = {Q-Map: Clinical Concept Mining from Clinical Documents},
  author    = {Azam, Sheikh Shams and Raju, Manoj and Pagidimarri, Venkatesh and Kasivajjala, Vamsi},
  journal   = {International Journal of Computer and Information Engineering (IJCIE)},
  year      = {2018},
  volume    = {12},
  number    = {9},
  pages     = {691 - 696},
  publisher = {World Academy of Science, Engineering and Technology},
  url     = {https://publications.waset.org/vol/141},
}

Workshop

[W2] Sheikh Shams Azam, Martin Pelikan, Vitaly Feldman, Kunal Talwar, Jan “Honza” Silovsky, and Tatiana Likhomanenko. “Federated Learning for Speech Recognition: Revisiting Current Trends Towards Large-Scale ASR.” In International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS, 2023.
[paper] [apple-ml] [poster] [slides]
@inproceedings{azam2023federated,
  title={Federated Learning for Speech Recognition: Revisiting Current Trends Towards Large-Scale {ASR}},
  author={Azam, Sheikh Shams and Pelikan, Martin and Feldman, Vitaly and Silovsky, Jan and Talwar, Kunal and Likhomanenko, Tatiana},
  booktitle={International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023},
  year={2023},
  url={https://openreview.net/forum?id=ozN92d7CHX}
}
[W1] Sheikh Shams Azam, Taejin Kim, Seyyedali Hosseinalipour, Christopher G. Brinton, Carlee Joe-Wong, and Saurabh Bagchi. “A Generalized and Distributable Generative Model for Private Representation Learning.” In NeurIPS Workshop on Deep Generative Models and Downstream Applications, 2021.
[paper] [poster] [code]
@inproceedings{azam2022eigan,
  title     = {Can we Generalize and Distribute Private Representation Learning?},
  author    = {Azam, Sheikh Shams and Kim, Taejin and Hosseinalipour, Seyyedali and Joe-Wong, Carlee and Bagchi, Saurabh and Brinton, Christopher G.},
  booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year      = {2022},
  series    = {Proceedings of Machine Learning Research},
  volume    = {151},
  pages     = {11320--11340},
  month     = {28--30 Mar},
  publisher = {PMLR},
  url       = {https://proceedings.mlr.press/v151/shams-azam22a.html}
}

Thesis

[T1] Sheikh Shams Azam. “Towards Privacy and Communication Efficiency in Distributed Representation Learning.” Purdue University Graduate School, 2022. DOI: 10.25394/PGS.20029550.v1.
[thesis]
@article{azam2022towardsprivacy, 
  title     = {Towards Privacy and Communication Efficiency in Distributed Representation Learning}, 
  author    = {Azam, Sheikh Shams}, 
  year      = {2022}, 
  month     = {6}, 
  publisher = {Purdue University Graduate School}
  url       = {https://hammer.purdue.edu/articles/thesis/Towards_Privacy_and_Communication_Efficiency_in_Distributed_Representation_Learning/20029550}, 
}