Portrait of Reihaneh Rabbany

Reihaneh Rabbany

Core Academic Member
reihaneh.rabbany@mila.quebec
Canada CIFAR AI Chair
Assistant Professor, McGill University, School of Computer Science
Research Topics
Data Mining
Graph Neural Networks
Learning on Graphs
Natural Language Processing
Representation Learning
Website
Google Scholar
LinkedIn

Biography

Reihaneh Rabbany is an assistant professor at the School of Computer Science, McGill University, and a core academic member of Mila – Quebec Artificial Intelligence Institute. She is also a Canada CIFAR AI Chair and on the faculty of McGill’s Centre for the Study of Democratic Citizenship.

Before joining McGill, Rabbany was a postdoctoral fellow at the School of Computer Science, Carnegie Mellon University. She completed her PhD in the Department of Computing Science at the University of Alberta.

Rabbany heads McGill’s Complex Data Lab, where she conducts research at the intersection of network science, data mining and machine learning, with a focus on analyzing real-world interconnected data and social good applications.

Current Students

Hussein Abdallah
Collaborating researcher - Concordia University
hussein.abdallah@mail.concordia.ca
Github
Aurélien Bück-Kaeffer
Master's Research - McGill University
Github
Jacob Chmura
Master's Research - McGill University
Principal supervisor :
Nicolas Le Roux
Website
Github
Aarash Feizi
PhD - McGill University
Co-supervisor :
Adriana Romero Soriano
Website
Github
Google Scholar
Shenyang Huang
Collaborating Alumni - McGill University
Co-supervisor :
Guillaume Rabusseau
Website
Github
Google Scholar
Emma Kondrup
Research Intern - McGill University
Website
Github
Google Scholar
Elahe Kooshafar
Master's Research - McGill University
Victor Livernoche
PhD - McGill University
Github
Google Scholar
Sitao Luan
Postdoctorate - McGill University
Principal supervisor :
Guillaume Rabusseau
Github
Google Scholar
Shahrad Mohammadzadeh
Master's Research - McGill University
Co-supervisor :
Doina Precup
Website
Github
Google Scholar
Pratheeksha Nair
Collaborating researcher - McGill University
Website
Github
Google Scholar
Sahar Omidi Shayegan
Master's Research - McGill University
Website
Github
Soroush Omranpour
Collaborating Alumni - McGill University
Co-supervisor :
Guillaume Rabusseau
Github
Kellin Pelrine
PhD - McGill University
kellin.pelrine@mila.quebec
Website
Google Scholar
Farimah Poursafaei
Collaborating Alumni - McGill University
Website
Github
Google Scholar
Max Puelma Touzel
Collaborating researcher
Website
Github
Google Scholar
Sebastian Sabry
Collaborating researcher - McGill University University
Github
Sneheel Sarangi
Collaborating researcher - McGill University
sneheelsarangi@gmail.com
Website
Github
Google Scholar
Alexandre St-Aubin
Research Intern - McGill University
Github
Vidya Sujaya
Master's Research - McGill University
Camille Thibault
Master's Research - Université de Montréal
Principal supervisor :
Jean-François Godbout
Website
Github
Google Scholar
Jacob-Junqi Tian
Collaborating researcher - McGill University
jacob.mila.handle@tianshome.com
Website
Github
Google Scholar
Aaron Tjandra
Collaborating researcher - Université de Montréal
Principal supervisor :
Guillaume Rabusseau
Website
Google Scholar
Zachary Yang
PhD - McGill University
Github
Google Scholar
Jie Zan
Research Intern - McGill University
jie.zan@mail.mcgill.ca
Github
Sveta Zhuk
Master's Research - Université de Montréal
Principal supervisor :
Jean-François Godbout

Publications

The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio
Tegan Maharaj
Luke Ong
Stuart Russell
Dawn Song
Max Tegmark
Lan Xue
Ya-Qin Zhang
Stephen Casper
Wan Sie Lee
Sören Mindermann
Vanessa Wilfred
Vidhisha Balachandran
Fazl Barez
Michael Belinsky
Imane Bello
Malo Bourgon
Mark Brakel
Sim'eon Campos
Duncan Cass-Beggs … (see 67 more)
Jiahao Chen
Rumman Chowdhury
Kuan Chua Seah
Jeff Clune
Juntao Dai
Agnès Delaborde
Nouha Dziri
Francisco Eiras
Joshua Engels
Jinyu Fan
Adam Gleave
Noah D. Goodman
Fynn Heide
Johannes Heidecke
Dan Hendrycks
Cyrus Hodes
Bryan Low Kian Hsiang
Minlie Huang
Sami Jawhar
Jingyu Wang
Adam Tauman Kalai
Meindert Kamphuis
Mohan S. Kankanhalli
Subhash Kantamneni
Mathias Bonde Kirk
Thomas Kwa
Jeffrey Ladish
Kwok-Yan Lam
Wan Lee Sie
Taewhi Lee
Xiaojian Li
Jiajun Liu
Chaochao Lu
Yifan Mai
Richard Mallah
Julian Michael
Nick Moës
Simon Möller
Kihyuk Nam
Kwan Yee Ng
Mark Nitzberg
Besmira Nushi
Sean O hEigeartaigh
Alejandro Ortega
Pierre Peigné
James Petrie
Benjamin Prud'homme
Reihaneh Rabbany
Nayat Sanchez-Pi
Sarah Schwettmann
Buck Shlegeris
Saad Siddiqui
Aradhana Sinha
Martín Soto
Cheston Tan
Dong Ting
William Tjhi
Robert Trager
Brian Tse
H. AnthonyTungK.
John Willes
Denise Wong
Wei Xu
Rongwu Xu
Yi Zeng 0005
HongJiang Zhang
Djordje Zikelic
2025-01-01
arXiv.org (preprint)
doi.org
Online Influence Campaigns: Strategies and Vulnerabilities
Andreea Musulan
Veronica Xia
Ethan Kosak-Hine
Tom Gibbs
Vidya Sujaya
Reihaneh Rabbany
Jean-François Godbout
Kellin Pelrine
U. Montr'eal
Ivado
M. University
In order to combat the creation and spread of harmful content online, this paper defines and contextualizes the concept of inauthentic, soci… (see more)etal-scale manipulation by malicious actors. We review the literature on societally harmful content and how it proliferates to analyze the manipulation strategies used by such actors and the vulnerabilities they target. We also provide an overview of three case studies of extensive manipulation campaigns to emphasize the severity of the problem. We then address the role that Artificial Intelligence plays in the development and dissemination of harmful content, and how its evolution presents new threats to societal cohesion for countries across the globe. Our survey aims to increase our understanding of not just particular aspects of these threats, but also the strategies underlying their deployment, so we can effectively prepare for the evolving cybersecurity landscape.
2024-12-18
ArXiv (preprint)
doi.org
arxiv.org
Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
In this paper, we tackle the challenge of predicting stock movements in financial markets by introducing Higher Order Transformers, a novel … (see more)architecture designed for processing multivariate time-series data. We extend the self-attention mechanism and the transformer architecture to a higher order, effectively capturing complex market dynamics across time and variables. To manage computational complexity, we propose a low-rank approximation of the potentially large attention tensor using tensor decomposition and employ kernel attention, reducing complexity to linear with respect to the data size. Additionally, we present an encoder-decoder model that integrates technical and fundamental analysis, utilizing multimodal signals from historical prices and related tweets. Our experiments on the Stocknet dataset demonstrate the effectiveness of our method, highlighting its potential for enhancing stock movement prediction in financial markets.
2024-12-13
ArXiv (preprint)
doi.org
arxiv.org
Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
In this paper, we tackle the challenge of predicting stock movements in financial markets by introducing Higher Order Transformers, a novel … (see more)architecture designed for processing multivariate time-series data. We extend the self-attention mechanism and the transformer architecture to a higher order, effectively capturing complex market dynamics across time and variables. To manage computational complexity, we propose a low-rank approximation of the potentially large attention tensor using tensor decomposition and employ kernel attention, reducing complexity to linear with respect to the data size. Additionally, we present an encoder-decoder model that integrates technical and fundamental analysis, utilizing multimodal signals from historical prices and related tweets. Our experiments on the Stocknet dataset demonstrate the effectiveness of our method, highlighting its potential for enhancing stock movement prediction in financial markets.
2024-12-13
ArXiv (preprint)
arxiv.org
arxiv.org
Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
In this paper, we tackle the challenge of predicting stock movements in financial markets by introducing Higher Order Transformers, a novel … (see more)architecture designed for processing multivariate time-series data. We extend the self-attention mechanism and the transformer architecture to a higher order, effectively capturing complex market dynamics across time and variables. To manage computational complexity, we propose a low-rank approximation of the potentially large attention tensor using tensor decomposition and employ kernel attention, reducing complexity to linear with respect to the data size. Additionally, we present an encoder-decoder model that integrates technical and fundamental analysis, utilizing multimodal signals from historical prices and related tweets. Our experiments on the Stocknet dataset demonstrate the effectiveness of our method, highlighting its potential for enhancing stock movement prediction in financial markets.
2024-12-13
ArXiv (preprint)
doi.org
arxiv.org
Higher Order Transformers: Efficient Attention Mechanism for Tensor Structured Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
Transformers are now ubiquitous for sequence modeling tasks, but their extension to multi-dimensional data remains a challenge due to the qu… (see more)adratic cost of the attention mechanism. In this paper, we propose Higher-Order Transformers (HOT), a novel architecture designed to efficiently process data with more than two axes, i.e. higher-order tensors. To address the computational challenges associated with high-order tensor attention, we introduce a novel Kronecker factorized attention mechanism that reduces the attention cost to quadratic in each axis' dimension, rather than quadratic in the total size of the input tensor. To further enhance efficiency, HOT leverages kernelized attention, reducing the complexity to linear. This strategy maintains the model's expressiveness while enabling scalable attention computation. We validate the effectiveness of HOT on two high-dimensional tasks, including multivariate time series forecasting, and 3D medical image classification. Experimental results demonstrate that HOT achieves competitive performance while significantly improving computational efficiency, showcasing its potential for tackling a wide range of complex, multi-dimensional data.
2024-12-04
ArXiv (preprint)
arxiv.org
arxiv.org
Higher Order Transformers: Efficient Attention Mechanism for Tensor Structured Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
Transformers are now ubiquitous for sequence modeling tasks, but their extension to multi-dimensional data remains a challenge due to the qu… (see more)adratic cost of the attention mechanism. In this paper, we propose Higher-Order Transformers (HOT), a novel architecture designed to efficiently process data with more than two axes, i.e. higher-order tensors. To address the computational challenges associated with high-order tensor attention, we introduce a novel Kronecker factorized attention mechanism that reduces the attention cost to quadratic in each axis' dimension, rather than quadratic in the total size of the input tensor. To further enhance efficiency, HOT leverages kernelized attention, reducing the complexity to linear. This strategy maintains the model's expressiveness while enabling scalable attention computation. We validate the effectiveness of HOT on two high-dimensional tasks, including multivariate time series forecasting, and 3D medical image classification. Experimental results demonstrate that HOT achieves competitive performance while significantly improving computational efficiency, showcasing its potential for tackling a wide range of complex, multi-dimensional data.
2024-12-04
ArXiv (preprint)
doi.org
arxiv.org
Higher Order Transformers: Efficient Attention Mechanism for Tensor Structured Data
Soroush Omranpour
Guillaume Rabusseau
Reihaneh Rabbany
Transformers are now ubiquitous for sequence modeling tasks, but their extension to multi-dimensional data remains a challenge due to the qu… (see more)adratic cost of the attention mechanism. In this paper, we propose Higher-Order Transformers (HOT), a novel architecture designed to efficiently process data with more than two axes, i.e. higher-order tensors. To address the computational challenges associated with high-order tensor attention, we introduce a novel Kronecker factorized attention mechanism that reduces the attention cost to quadratic in each axis' dimension, rather than quadratic in the total size of the input tensor. To further enhance efficiency, HOT leverages kernelized attention, reducing the complexity to linear. This strategy maintains the model's expressiveness while enabling scalable attention computation. We validate the effectiveness of HOT on two high-dimensional tasks, including multivariate time series forecasting, and 3D medical image classification. Experimental results demonstrate that HOT achieves competitive performance while significantly improving computational efficiency, showcasing its potential for tackling a wide range of complex, multi-dimensional data.
2024-12-04
ArXiv (preprint)
doi.org
openreview.net
A Guide to Misinformation Detection Data and Evaluation
Camille Thibault
Jacob-Junqi Tian
Gabrielle Péloquin-Skulski
Taylor Lynn Curtis
James Zhou
Florence Laflamme
Yuxiang Guan
Reihaneh Rabbany
Jean-François Godbout
Kellin Pelrine
2024-11-07
ArXiv (preprint)
arxiv.org
arxiv.org
Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training
Shahrad Mohammadzadeh
Juan David Guerra
Marco Bonizzato
Reihaneh Rabbany
Golnoosh Farnadi
As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due … (see more)to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M - 12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed. This efficient metric is integrated into our protocol, allowing SenD to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to Wikipedia, Medical, and LegalBench domains.
2024-10-20
ArXiv (preprint)
doi.org
arxiv.org
Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training
Shahrad Mohammadzadeh
Juan David Guerra
Marco Bonizzato
Reihaneh Rabbany
Golnoosh Farnadi
As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due … (see more)to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M - 12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed. This efficient metric is integrated into our protocol, allowing SenD to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to Wikipedia, Medical, and LegalBench domains.
2024-10-20
ArXiv (preprint)
arxiv.org
arxiv.org
Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training
Shahrad Mohammadzadeh
Juan David Guerra
Marco Bonizzato
Reihaneh Rabbany
Golnoosh Farnadi
2024-10-20
ArXiv (preprint)
arxiv.org
arxiv.org