Reihaneh Rabbany

hussein.abdallah@mail.concordia.ca

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

Postdoctorate - McGill University

oumaima.amezgar@mila.quebec

Oumaima Amezgar

PhD - Université de Montréal

Aurélien Bück-Kaeffer

Master's Research - McGill University

aurelien.buck-kaeffer@mila.quebec

Andrea Cini

Independent visiting researcher - Mila

Research Intern - Université de Montréal

mcorriveau303@gmail.com

Johnny Dellas

PhD - McGill University

john.dellas@mila.quebec

Islam Eldifrawi

Independent visiting researcher - University of Sherbrooke

sulum821991@gmail.com

sophia.garrel@mila.quebec

Aarash Feizi

PhD - McGill University

Co-supervisor :

Adriana Romero Soriano

Collaborating researcher - McGill University

nicholas.gaudet@mila.quebec

Nicholas Gaudet

PhD - Université de Montréal

mattia.greiche@mila.quebec

Mattia Greiche

Research Intern - McGill University

Nazia Hossain

Research Intern - McGill University University

nazia.hossain@mila.quebec

Anne Imouza

PhD - McGill University

anne.imouza@mila.quebec

Emma Kondrup

PhD - McGill University

Co-supervisor :

Catherine Régis

emma.kondrup@mila.quebec

Andrew Lin

Research Intern - McGill University University

andrew.lin@mila.quebec

victor.livernoche@mila.quebec

Victor Livernoche

PhD - McGill University

shahrad.mohammadzadeh@mila.quebec

Sitao Luan

Postdoctorate - McGill University

Principal supervisor :

Shahrad Mohammadzadeh

Master's Research - McGill University

Co-supervisor :

Doina Precup

Collaborating Alumni - McGill University

farimah.poursafaei@mila.quebec

PhD - Université de Montréal

meissa.rebbani@mila.quebec

sebastian.sabry@mila.quebec

Sebastian Sabry

Master's Research - McGill University University

dorsaf.sallami@mila.quebec

Dorsaf Sallami

Independent visiting researcher - McGill University

jacob.mila.handle@tianshome.com

Sneheel Sarangi

Master's Research - McGill University

sneheelsarangi@gmail.com

Master's Research - McGill University University

shiyan.wliu@gmail.com

Jacob-Junqi Tian

Master's Research - McGill University

Collaborating researcher - Université de Montréal

Principal supervisor :

Guillaume Rabusseau

aaron.tjandra@mila.quebec

chin-chen.yang@mila.quebec

Li Wei Wang

Research Intern - McGill University

liweiwang2002@gmail.com

Tong Wu

Collaborating researcher - McGill University University

PhD - McGill University

Brian Yang

PhD - McGill University

brian.yang@mila.quebec

Master's Research - McGill University

xueli.zhao@mila.quebec

svetlana.zhuk@mila.quebec

Sveta Zhuk

Master's Research - Université de Montréal

Blog Posts

Un groupe hétéroclite de huit jeunes adultes se tient serré sur un toit, souriant et riant avec la silhouette de la ville en arrière-plan. Deux encarts circulaires mettent en évidence une caméra vintage tenue par l'un des membres du groupe, soulignant l'élément deepfake.

December 16, 2025

Unmasking deepfakes with AI

Victor Livernoche

Reihaneh Rabbany

Read the article

August 3, 2021

Flight-SEIR: Incorporating Flight Data to Improve Epidemiological Modelling and Disease Outbreak Prevention

Shenyang Huang

Reihaneh Rabbany

Read the article

Publications

Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation

Mauricio Rivera

2024-01-12

ArXiv (preprint)

Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation

Tyler Vergho

Recent large language models (LLMs) have been shown to be effective for misinformation detection. However, the choice of LLMs for experiment… (see more)s varies widely, leading to uncertain conclusions. In particular, GPT-4 is known to be strong in this domain, but it is closed source, potentially expensive, and can show instability between different versions. Meanwhile, alternative LLMs have given mixed results. In this work, we show that Zephyr-7b presents a consistently viable alternative, overcoming key limitations of commonly used approaches like Llama-2 and GPT-3.5. This provides the research community with a solid open-source option and shows open-source models are gradually catching up on this task. We then highlight how GPT-3.5 exhibits unstable performance, such that this very widely used model could provide misleading results in misinformation detection. Finally, we validate new tools including approaches to structured output and the latest version of GPT-4 (Turbo), showing they do not compromise performance, thus unlocking them for future research and potentially enabling more complex pipelines for misinformation mitigation.

2024-01-11

ArXiv (preprint)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning

Aarash Feizi

Randall Balestriero

Arantxa Casanova

Adriana Romero

We propose Guided Positive Sampling Self-Supervised Learning (GPS-SSL), a general method to inject a priori knowledge into Self-Supervised L… (see more)earning (SSL) positive samples selection. Current SSL methods leverage Data-Augmentations (DA) for generating positive samples and incorporate prior knowledge - an incorrect, or too weak DA will drastically reduce the quality of the learned representation. GPS-SSL proposes instead to design a metric space where Euclidean distances become a meaningful proxy for semantic relationship. In that space, it is now possible to generate positive samples from nearest neighbor sampling. Any prior knowledge can now be embedded into that metric space independently from the employed DA. From its simplicity, GPS-SSL is applicable to any SSL method, e.g. SimCLR or BYOL. A key benefit of GPS-SSL is in reducing the pressure in tailoring strong DAs. For example GPS-SSL reaches 85.58% on Cifar10 with weak DA while the baseline only reaches 37.51%. We therefore move a step forward towards the goal of making SSL less reliant on DA. We also show that even when using strong DAs, GPS-SSL outperforms the baselines on under-studied domains. We evaluate GPS-SSL along with multiple baseline SSL methods on numerous downstream datasets from different domains when the models use strong or minimal data augmentations. We hope that GPS-SSL will open new avenues in studying how to inject a priori knowledge into SSL in a principled manner.

2024-01-02

ArXiv (preprint)

Uncertainty Resolution in Misinformation Detection

Yury Orlovskiy

Camille Thibault

Anne Imouza

2024-01-01

arXiv (preprint)

An Evaluation of Language Models for Hyperpartisan Ideology Detection in Persian Twitter

Sahar Omidi Shayegan

Isar Nejadgholi

Hao Yu

Sacha Lévy

Zachary Yang

Large Language Models (LLMs) have shown significant promise in various tasks, including identifying the political beliefs of English-speakin… (see more)g social media users from their posts. However, assessing LLMs for this task in non-English languages remains unexplored. In this work, we ask to what extent LLMs can predict the political ideologies of users in Persian social media. To answer this question, we first acknowledge that political parties are not well-defined among Persian users, and therefore, we simplify the task to a much simpler task of hyperpartisan ideology detection. We create a new benchmark and show the potential and limitations of both open-source and commercial LLMs in classifying the hyper-partisan ideologies of users. We compare these models with smaller fine-tuned models, both on the Persian language (ParsBERT) and translated data (RoBERTa), showing that they considerably outperform generative LLMs in this task. We further demonstrate that the performance of the generative LLMs degrades when classifying users based on their tweets instead of their bios and even when tweets are added as additional information, whereas the smaller fine-tuned models are robust and achieve similar performance for all classes. This study is a first step toward political ideology detection in Persian Twitter, with implications for future research to understand the dynamics of ideologies in Persian social media.

2023-12-31

EURALI (published)

www.semanticscholar.org

Quantifying learning-style adaptation in effectiveness of LLM teaching

Ruben Weijers

Gabrielle Fidelis de Castilho

This preliminary study aims to investigate whether AI, when prompted based on individual learning styles, can effectively improve comprehens… (see more)ion and learning experiences in educational settings. It involves tailoring LLMs baseline prompts and comparing the results of a control group receiving standard content and an experimental group receiving learning style-tailored content. Preliminary results suggest that GPT-4 can generate responses aligned with various learning styles, indicating the potential for enhanced engagement and comprehension. However, these results also reveal challenges, including the model’s tendency for sycophantic behavior and variability in responses. Our findings suggest that a more sophisticated prompt engineering approach is required for integrating AI into education (AIEd) to improve educational outcomes.

2023-12-31

PERSONALIZE @ AAAI Conference on Artificial Intelligence (published)

Exhaustive Evaluation of Dynamic Link Prediction

Farimah Poursafaei

Dynamic link prediction is a crucial task in the study of evolving graphs, which serve as abstract models for various real-world application… (see more)s. Recent dynamic graph representation learning models have claimed near-perfect performance in this task. However, we argue that the standard evaluation strategy for dynamic link prediction overlooks the sparsity and recurrence patterns inherent in dynamic networks. Specifically, the current strategy suffers from issues such as evaluating models on a balanced set of positive and negative edges, neglecting the reassessment of frequently recurring positive edges, and lacking a comprehensive evaluation of both recurring and new edges.To address these limitations, we propose a novel evaluation strategy called EXHAUSTIVE, which takes into account all relevant negative edges and separately assesses the performance on recurring and new edges. Using our proposed evaluation strategy, we compare the performance of five state-of-the-art dynamic graph learning models on seven benchmark datasets. Compared to the previous common evaluation strategy, we observe an average drop of 62% in Average Precision for dynamic link prediction. Additionally, the ranking of the models also changes under the new evaluation setting. Furthermore, we demonstrate that while all models perform considerably worse when predicting new edges compared to recurring ones, the best performing models differ between the two scenarios. This highlights the importance of employing the proposed evaluation strategy for both the assessment and design of dynamic link prediction models. By adopting our novel evaluation strategy, researchers can obtain a more accurate understanding of model performance in dynamic link prediction, leading to improved evaluation and design of such models.

2023-12-03

2023 IEEE International Conference on Data Mining Workshops (ICDMW) (published)

SWEET: Weakly Supervised Person Name Extraction for Fighting Human Trafficking

Javin Liu

Hao Yu

2023-11-30

Findings of the Association for Computational Linguistics: EMNLP 2023 (published)

Towards Detecting Contextual Real-Time Toxicity for In-Game Chat

Zachary Yang

Nicolas Grenon-Godbout

Real-time toxicity detection in online environments poses a significant challenge, due to the increasing prevalence of social media and gami… (see more)ng platforms. We introduce ToxBuster, a simple and scalable model that reliably detects toxic content in real-time for a line of chat by including chat history and metadata. ToxBuster consistently outperforms conventional toxicity models across popular multiplayer games, including Rainbow Six Siege, For Honor, and DOTA 2. We conduct an ablation study to assess the importance of each model component and explore ToxBuster's transferability across the datasets. Furthermore, we showcase ToxBuster's efficacy in post-game moderation, successfully flagging 82.1% of chat-reported players at a precision level of 90.0%. Additionally, we show how an additional 6% of unreported toxic players can be proactively moderated.

2023-11-30

Findings of the Association for Computational Linguistics: EMNLP 2023 (published)

Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4

Anne Imouza

Meilina Reksoprodjo

Camille Thibault

Caleb Gupta

Joel Christoph

Published online: 24 May 2023

2023-11-30

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (published)

Laplacian Change Point Detection for Single and Multi-view Dynamic Graphs

Samy Coulombe

Dynamic graphs are rich data structures that are used to model complex relationships between entities over time. In particular, anomaly dete… (see more)ction in temporal graphs is crucial for many real world applications such as intrusion identification in network systems, detection of ecosystem disturbances and detection of epidemic outbreaks. In this paper, we focus on change point detection in dynamic graphs and address three main challenges associated with this problem: i). how to compare graph snapshots across time, ii). how to capture temporal dependencies, and iii). how to combine different views of a temporal graph. To solve the above challenges, we first propose Laplacian Anomaly Detection (LAD) which uses the spectrum of graph Laplacian as the low dimensional embedding of the graph structure at each snapshot. LAD explicitly models short term and long term dependencies by applying two sliding windows. Next, we propose MultiLAD, a simple and effective generalization of LAD to multi-view graphs. MultiLAD provides the first change point detection method for multi-view dynamic graphs. It aggregates the singular values of the normalized graph Laplacian from different views through the scalar power mean operation. Through extensive synthetic experiments, we show that i). LAD and MultiLAD are accurate and outperforms state-of-the-art baselines and their multi-view extensions by a large margin, ii). MultiLAD's advantage over contenders significantly increases when additional views are available, and iii). MultiLAD is highly robust to noise from individual views. In five real world dynamic graphs, we demonstrate that LAD and MultiLAD identify significant events as top anomalies such as the implementation of government COVID-19 interventions which impacted the population mobility in multi-view traffic networks.

2023-11-05

ACM Transactions on Knowledge Discovery from Data (published)

Temporal Graph Benchmark for Machine Learning on Temporal Graphs

Shenyang Huang

Farimah Poursafaei

Jacob Danovitch

Matthias Fey

Weihua Hu

Emanuele Rossi

Jure Leskovec

Michael M. Bronstein

Guillaume Rabusseau

We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and r… (see more)obust evaluation of machine learning models on temporal graphs. TGB datasets are of large scale, spanning years in duration, incorporate both node and edge-level prediction tasks and cover a diverse set of domains including social, trade, transaction, and transportation networks. For both tasks, we design evaluation protocols based on realistic use-cases. We extensively benchmark each dataset and find that the performance of common models can vary drastically across datasets. In addition, on dynamic node property prediction tasks, we show that simple methods often achieve superior performance compared to existing temporal graph models. We believe that these findings open up opportunities for future research on temporal graphs. Finally, TGB provides an automated machine learning pipeline for reproducible and accessible temporal graph research, including data loading, experiment setup and performance evaluation. TGB will be maintained and updated on a regular basis and welcomes community feedback. TGB datasets, data loaders, example codes, evaluation setup, and leaderboards are publicly available at https://tgb.complexdatalab.com/.

2023-09-24

NeurIPS.cc/2023/Track/Datasets_and_Benchmarks (poster)