School of Computer Science Colloquium #3 Presentation by Dr. Majid Afshar:"Large-Scale Dimensionality Reduction Using Singular Vectors "

Friday, October 8, 2021 - 11:00 to 12:30


The School of Computer Science at the University of Windsor is pleased to present…  

Colloquium Presentation #3 by Dr. Majid Afshar 

Picture of Dr. Ashraf Majid, School of Computer Science Post Doctoral Fellow_Oct.4, 2021
Date: Friday October 8, 2021 
Time: 11:00am – 12:30pm 
Passcode: If interested in attending this event, contact the Graduate Secretary at with suffient notice before the event to obtain the passcode.


Massive volumes of high-dimensional data have become pervasive, with the number of features significantly exceeding the number of samples in many applications. This has resulted in a bottleneck for data mining applications and amplified the computational burden of machine learning algorithms that perform classification or pattern recognition. Dimensionality reduction can handle this problem in two ways, i.e. feature selection (FS) and feature extraction. We focus on FS, because, in many applications like bioinformatics, the domain experts need to validate a set of original features to corroborate the hypothesis of the prediction models. In processing the high-dimensional data, FS mainly involves detecting a limited number of important features among tens/hundreds of thousands of irrelevant and redundant features. 
We start with filtering the irrelevant features using our proposed Sparse Least Squares (SLS) method, where a score is assigned to each feature, and the low-scoring features are removed using a soft threshold. Then, we proposed a new Singular Vectors FS (SVFS) method that is capable of both removing the irrelevant features and effectively clustering the remaining features. As such, the features in each cluster solely exhibit inner correlations with each other. The independently selected important features from different clusters comprise the final rank. Devising thresholds for filtering irrelevant and redundant features has facilitated the adaptability of our model to the particular needs of various applications. 
A comprehensive evaluation based on benchmark biological and image datasets shows the superiority of our proposed methods compared to the state-of-the-art FS methods in terms of classification accuracy, running time, and memory usage. 


I am a Mitacs Elevate postdoctoral fellow at the School of Computer Science, University of Windsor , working with Dr. Saeed Samet , focusing on defining the underlying structures in unlabeled sensor data. 
I received my Ph.D. from the Department of Computer Science, Memorial University of Newfoundland, under supervision of Dr. Hamid Usefi and Dr. Saeed Samet, where I proposed and developed a new dimensionality reduction and scalable feature selection method called singular vectors feature selection.  
Vector Institute of Artificial Intelligence, artificial intelligence approved logo
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 (working remotely)