My name is Reza Namazi. I'm a B.Sc Computer Engineering student at Sharif University of Technology - Kish International Campus.
In my leisure time I enjoy playing the piano, watching movies, cycling and bowling.
In my free time, I also enjoy programming for fun.
Sharif University of Technology - International Campus, Kish Island, Iran
Expected graduation: Winter 2021
Shahid Beheshti (NODET*), Ahvaz, Iran
Graduation: Spring 2016
Graph is an abstract data type that arise in many fields and applications. Graphs have proven to be a very
useful data representation medium since they reveal a lot of information about the system that is being
analyzed. This fact had led to an increasing interest to understand graphs better and to reveal the hidden
information that is contained in them.
My main research interest is learning low-dimensional representations of graphs using machine learning approaches. I have been studying this topic and learning about different researches that have been done in this field. I also try to apply my own ideas to improve the results of the existing methods and gain better results than the existing methods.
Namazi, R., Zolanvari, A., Sani, M. and Ghahramani, S.A.A.G., 2020. GL-Coarsener: A
graph representation learning framework to construct coarse grid hierarchy for AMG solvers. arXiv
preprint arXiv:2011.09994 [pdf] [code]
Abstract: In many numerical schemes, the computational complexity scales non-linearly with the problem size. Solving a linear system of equations using direct methods or most iterative methods is a typical example. Algebraic multi-grid (AMG) methods are numerical methods used to solve large linear systems of equations efficiently. One of the main differences between AMG methods is how the coarser grid is constructed from a given fine grid. There are two main classes of AMG methods; graph and aggregation based coarsening methods. Here we propose an aggregation-based coarsening framework leveraging graph representation learning and clustering algorithms. Our method introduces the power of machine learning into the AMG research field and opens a new perspective for future researches. The proposed method uses graph representation learning techniques to learn latent features of the graph obtained from the underlying matrix of coefficients. Using these extracted features, we generated a coarser grid from the fine grid. The proposed method is highly capable of parallel computations. Our experiments show that the proposed method's efficiency in solving large systems is closely comparable with other aggregation-based methods, demonstrating the high capability of graph representation learning in designing multi-grid solvers.
Sharif University of Technology, Kish, Iran - 2020 [link]
Optimizing Algebraic Multigrid Methods for large sparse algebraic systems of equations using parallel processing and machine learning techniques under the supervisory of Dr. M.Sani and Dr. A.A. G.Ghahremani.
Given a list of nodes and edges, it is possible to visualize the graph in a 2-dimensional plane in an unlimited number of ways. In this project, I tried to find the "best" representation (aesthetically pleasing) of the given graph using force-directed layout algorithm.
In this project I tried to analyze an epidemic with infection rate α and recovery rate β in an SIS (Susceptible - Infected - Susceptible) model. Graphing the number of infected and susceptible nodes of the population in different steps of the epidemic reveals the epidemic threshold of the epidemic and much more!
Sharif University of Technology, Kish, Iran - March 2020
Numerical Methods course offered by Dr. A.A. G.Ghahremani
Sharif University of Technology, Kish, Iran - October 2019 [link]
Engineering Probability and Statistics course offered by Dr. A.A. G.Ghahremani
Sharif University of Technology, Kish, Iran - March 2019 [link]
Basics of Programming course offered by Dr. M. Sani
IPM School of Cognitive Science (SCS), Tehran, Iran - August 2019 [link]
Attended IPM summer school covering Machine Learning, Deep Learning, Machine Vision and Reinforcement Learning and passed the evaluation test
Top student in Computer Engineering department of Sharif University of Technology - December 2018 [link]