Narges Armanfard

Membre académique associé

Professeure adjointe, McGill University, Département de génie électrique et informatique

Sujets de recherche

Apprentissage automatique médical

Apprentissage de représentations

Apprentissage en ligne

Apprentissage multimodal

Apprentissage par renforcement

Apprentissage profond

Réseaux de neurones en graphes

Site web

Google Scholar

Biographie

Narges Armanfard (Ph. D., ing.) est la fondatrice et la chercheuse principale du laboratoire iSMART. Elle est professeure adjointe au Département de génie électrique et informatique de l'Université McGill et membre académique associé à Mila – Institut québécois d'intelligence artificielle. Elle est également affiliée au Centre sur les machines intelligentes de McGill (CIM), à l'Initiative de McGill en médecine computationnelle (MiCM) et à l'Institut de génie aérospatial de McGill (MIAE). Sa recherche porte sur le développement d'algorithmes novateurs pour divers domaines tels que l'analyse de données de séries temporelles, la vision par ordinateur, l'apprentissage par renforcement et l'apprentissage par représentation pour des tâches telles que le regroupement de données, la classification et la détection d'anomalies. Ses contributions au domaine de l'IA ont été reconnues par de nombreux prix, décernés notamment par le Conseil de recherches en sciences naturelles et en génie du Canada, AgeWell, Vanier-Banting, les Fonds de recherche du Québec, ainsi que l'Université McMaster, l'Université McGill, l'Université de Toronto, les Instituts de recherche en santé du Canada et Scale AI.

Étudiants actuels

Cormac Cureton

Maîtrise recherche - McGill

Site web

Github

Khanh Ho Ho

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Thomas Lai

Doctorat - McGill

Abhijeet Praveen

Maîtrise recherche - McGill

Github

Aman Sidhu

Maîtrise recherche - McGill

Doctorat - McGill

Zihan Wang

Maîtrise recherche - McGill

Co-superviseur⋅e :

Samira Ebrahimi Kahou

Site web

Google Scholar

Publications

Spatio-temporal hard attention learning for skeleton-based activity recognition

Bahareh Nikpour

Narges Armanfard

2023-02-01

Pattern Recognition (publié)

doi.org

Graph-based Time-Series Anomaly Detection: A Survey

Thi Kieu Khanh Ho

Ali Karami

Narges Armanfard

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 … (voir plus)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.

2023-01-31

ArXiv (prépublication)

doi.org

arxiv.org

DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection

Hadi Hojjati

Narges Armanfard

Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data. With recent adv… (voir plus)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.

2023-01-01

IEEE Transactions on Knowledge and Data Engineering (publié)

doi.org

arxiv.org

How can intelligent systems revolutionise healthcare?

Narges Armanfard

2023-01-01

Futurum Careers (publié)

doi.org

Multivariate Time-Series Anomaly Detection with Temporal Self-supervision and Graphs: Application to Vehicle Failure Prediction

Hadi Hojjati

Mohammadreza Sadeghi