I’m Ryien (IPA: rɑːjin, Persian: رایین), a PhD student in
the Department of Computer Science
at the University of Chicago, where I am advised
by Hank Hoffmann and Rebecca Willett.
My research interests lie at the intersection of machine learning and dynamic systems.
I am broadly interested in developing adaptive machine learning algorithms, or algorithms
that dynamically adjust their behavior in response to changes in input data
distribution or attributes, performance constraints, changing levels of supervision, and other
evolving factors.
Previously, I was a Predoctoral researcher at the
Leadership Computing Facility
at Argonne National Laboratory, where I worked with Venkatram
Vishwanath and Filippo
Simini
to develop and scale graph neural networks (GNNs) for scientific applications.
I received my M.S. through the Electrical and Computer
Engineering Department at the
University of Michigan,
where my focus was on machine learning, systems, and computational biology. Prior to attending
graduate school, I
received my undergraduate degrees in computer engineering
(B.S.E.) and cognitive science (B.S.),
also at the University of Michigan.
Ryien Hosseini
PhD Student
Department of Computer Science
University of Chicago
Curriculum Vitae
Office: JCL 381
Mailing Address: 5730 S Ellis Ave, Chicago, IL 60637
Email: ryien [at] uchicago [dot] edu
Google Scholar |
Github |
LinkedIn
Publications
Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Rebecca Willett, Henry Hoffmann
The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)
(To
appear)
Quality Measures for Dynamic Graph Generative Models
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Rebecca Willett, Henry Hoffmann
The 13th International Conference on Learning Representations (ICLR 2025) (Spotlight)
[Paper]
[Arxiv]
[Code]
A Deep Probabilistic Framework for Continuous Time
Dynamic Graph Generation
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Henry Hoffmann
The 39th AAAI Conference on Artificial Intelligence (AAAI 2025)
[Paper]
[Arxiv]
[Code]
Exploring the Use of Dataflow Architectures for Graph Neural Network Workloads
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Ramakrishnan Sivakumar, Sanjif
Shanmugavelu, Zhengyu Chen, Lev Zlotnik, Mingran Wang, Philip Colangelo, Andrew Deng,
Philip Lassen, Shukur Pathan
Workshop on HPC on Heterogeneous Hardware, held at the 38th International Conference on High
Performance Computing (ISC 2023)
[Paper]
Piloting a Flexible Deadline Policy for a First-Year Computer Programming Course
Isha Bhatt, Laura K Alford, Lesa Begley, Ryien Hosseini, Deborah A Lichti
American Society for Engineering Education Annual Conference (ASEE 2023)
[Paper]
Deep Surrogate Docking: Accelerating Automated Drug Discovery with Graph Neural Networks
Ryien Hosseini, Filippo Simini, Austin Clyde, Arvind Ramanathan
Workshop on AI for Science, held at the 36th Conference on Neural Information Processing Systems
(Neurips 2022)
[Paper]
[Arxiv]
[Code]
Operation-Level Performance Benchmarking of Graph Neural Networks for Scientific Applications
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath
Workshop on Benchmarking Machine Learning Workloads on Emerging Hardware, held at the 5th
Conference on Machine Learning and Systems (MLSys 2022)
[Arxiv]
[Code]
Teaching
Graduate Student Instructor, University of Michigan
Course:
Engr 101: Introduction to Computers and Programming
Instructional Aide (Undergraduate), University of Michigan
Course:
EECS 280: Programming and Introductory Data Structures
Contact
Email: ryien [at] uchicago [dot] edu
Google
Scholar
Github
LinkedIn