Portrait of Narges Armanfard

Narges Armanfard

Associate Academic Member
Assistant Professor, McGill University, Department of Electrical and Computer Engineering
Research Topics
Deep Learning
Graph Neural Networks
Medical Machine Learning
Multimodal Learning
Online Learning
Reinforcement Learning
Representation Learning

Biography

Narges Armanfard (PhD, PEng) is the Founder and Principal Investigator of McGill University’s iSMART Lab. She's a tenure-track Assistant professor in the Department of Electrical and Computer Engineering at McGill and an Associate Academic member at Mila – Quebec Artificial Intelligence Institute.

Armanfard is also affiliated with McGill’s Centre for Intelligent Machines (CIM), the McGill initiative in Computational Medicine (MiCM), and the McGill Institute for Aerospace Engineering (MIAE).

Her research focuses on developing innovative algorithms for various domains, such as time-series data analysis, computer vision, reinforcement learning and representation learning for tasks like data clustering, classification and anomaly detection.

Her contributions to the field of AI have been recognized with numerous awards from a variety of institutions, including the Natural Sciences and Engineering Research Council of Canada, AgeWell, Vanier-Banting and the Fonds de recherche du Québec, as well as McMaster University, McGill University, the University of Toronto, the Canadian Institutes of Health Research and Scale AI.

Current Students

Master's Research - McGill University
PhD - McGill University
PhD - McGill University
PhD - McGill University
PhD - McGill University
Master's Research - McGill University
Master's Research - McGill University
PhD - McGill University
Master's Research - McGill University
Co-supervisor :
Master's Research - McGill University

Publications

Spatio-temporal hard attention learning for skeleton-based activity recognition
Bahareh Nikpour
Graph-based Time-Series Anomaly Detection: A Survey
Thi Kieu Khanh Ho
Ali Karami
With the recent advances in technology, a wide range of systems continue to collect a large amount of data over time and thus generate time … (see more)series. Time-Series Anomaly Detection (TSAD) is an important task in various time-series applications such as e-commerce, cybersecurity, vehicle maintenance, and healthcare monitoring. However, this task is very challenging as it requires considering both the intra-variable dependency and the inter-variable dependency, where a variable can be defined as an observation in time series data. Recent graph-based approaches have made impressive progress in tackling the challenges of this field. In this survey, we conduct a comprehensive and up-to-date review of Graph-based TSAD (G-TSAD). First, we explore the significant potential of graph representation learning for time-series data. Then, we review state-of-the-art graph anomaly detection techniques in the context of time series and discuss their strengths and drawbacks. Finally, we discuss the technical challenges and potential future directions for possible improvements in this research field.
DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection
Hadi Hojjati
Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data. With recent adv… (see more)ancements in deep learning, researchers have designed efficient deep anomaly detection methods. Existing works commonly use neural networks to map the data into a more informative representation and then apply an anomaly detection algorithm. In this paper, we propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hyper-sphere on its latent representation. We propose an anomaly score which is a combination of autoencoder's reconstruction error and the distance from the center of the enclosing hypersphere in the latent representation. Minimizing this anomaly score aids us in learning the underlying distribution of the normal class during training. Including the reconstruction error in the anomaly score ensures that DASVDD does not suffer from the common hypersphere collapse issue since the DASVDD model does not converge to the trivial solution of mapping all inputs to a constant point in the latent representation. Experimental evaluations on several benchmark datasets show that the proposed method outperforms the commonly used state-of-the-art anomaly detection algorithms while maintaining robust performance across different anomaly classes.
How can intelligent systems revolutionise healthcare?
Multivariate Time-Series Anomaly Detection with Temporal Self-supervision and Graphs: Application to Vehicle Failure Prediction
Hadi Hojjati
Mohammadreza Sadeghi
Multistep networks for roll force prediction in hot strip rolling mill
Shuh-Rong Shen
Denzel Guye
Xiaoping Ma
S. Yue
Multistep networks for roll force prediction in hot strip rolling mill
Shuh-Rong Shen
Denzel Guye
Xiaoping Ma
S. Yue