Publications

Low Compute Unlearning via Sparse Representations
Vedant Shah
Frederik Träuble
Ashish Malik
Hugo Larochelle
Michael Curtis Mozer
Sanjeev Arora
Yoshua Bengio
Anirudh Goyal
Machine unlearning, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible … (see more)using existing techniques. We propose a low-compute unlearning technique based on a discrete representational bottleneck. We show that the proposed technique efficiently unlearns the forget set and incurs negligible damage to the model's performance on the rest of the dataset. We evaluate the proposed technique on the problem of class unlearning using four datasets: CIFAR-10, CIFAR-100, LACUNA-100 and ImageNet-1k. We compare the proposed technique to SCRUB, a state-of-the-art approach which uses knowledge distillation for unlearning. Across all four datasets, the proposed technique performs as well as, if not better than SCRUB while incurring almost no computational cost.
2025-09-15
TMLR (accepted)
openreview.net
openreview.net
Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training
Hiroki Naganuma
Xinzhi Zhang
Man-Chung Yue
Ioannis Mitliagkas
Russell J. Hewett
Philipp Andre Witte
Yin Tat Lee
2025-09-15
TMLR (accepted)
openreview.net
openreview.net
Hitting the right pitch: Cortical tracking of speech fundamental frequency in auditory and somatomotor regions
Yorguin-Jose Mantilla-Ramos
Ana-Sofía Hincapié-Casas
Annalisa Pascarella
Tarek Lajnef
Richard M. Leahy
Emily B.J. Coffey
Karim Jerbi
Véronique Boulenger
Low-frequency neural oscillations contribute to the parsing of continuous speech into linguistic units. Little is known however on the coupl… (see more)ing of brain rhythms to higher-frequencies in speech such as fundamental frequency (F0) or pitch. Using magnetoencephalography, we investigated whole-brain cortical tracking of F0 while participants listened to sentences produced at normal rate or fast rate, where pitch naturally increases, and to artificially accelerated sentences, where F0 remains unchanged. Our results revealed significant brain-to-F0 coupling across all speech rates not only in right auditory but also in right parietal, insular, and pre- and postcentral regions, likely including the ventral larynx area. Importantly, the cortico-acoustic coupling peak frequency was higher for natural fast speech to reflect the corresponding F0 increase compared to normal rate and time-compressed speech. These findings demonstrate the engagement of an auditory-somato-motor network in F0 tracking, supporting its role in facilitating phonemic processing during the perception of naturally-produced speech.
2025-09-13
bioRxiv (preprint)
doi.org
Building a General SimCLR Self-Supervised Foundation Model Across Neurological Diseases to Advance 3D Brain MRI Diagnoses
Emily Kaczmarek
Justin Szeto
Brennan Nichyporuk
Tal Arbel
3D structural Magnetic Resonance Imaging (MRI) brain scans are commonly acquired in clinical settings to monitor a wide range of neurologica… (see more)l conditions, including neurodegenerative disorders and stroke. While deep learning models have shown promising results analyzing 3D MRI across a number of brain imaging tasks, most are highly tailored for specific tasks with limited labeled data, and are not able to generalize across tasks and/or populations. The development of self-supervised learning (SSL) has enabled the creation of large medical foundation models that leverage diverse, unlabeled datasets ranging from healthy to diseased data, showing significant success in 2D medical imaging applications. However, even the very few foundation models for 3D brain MRI that have been developed remain limited in resolution, scope, or accessibility. In this work, we present a general, high-resolution SimCLR-based SSL foundation model for 3D brain structural MRI, pre-trained on 18,759 patients (44,958 scans) from 11 publicly available datasets spanning diverse neurological diseases. We compare our model to Masked Autoencoders (MAE), as well as two supervised baselines, on four diverse downstream prediction tasks in both in-distribution and out-of-distribution settings. Our fine-tuned SimCLR model outperforms all other models across all tasks. Notably, our model still achieves superior performance when fine-tuned using only 20% of labeled training samples for predicting Alzheimer's disease. We use publicly available code and data, and release our trained model at https://github.com/emilykaczmarek/3D-Neuro-SimCLR, contributing a broadly applicable and accessible foundation model for clinical brain MRI analysis.
2025-09-12
ArXiv (preprint)
doi.org
arxiv.org
Building a General SimCLR Self-Supervised Foundation Model Across Neurological Diseases to Advance 3D Brain MRI Diagnoses
Emily Kaczmarek
Justin Szeto
Brennan Nichyporuk
Tal Arbel
3D structural Magnetic Resonance Imaging (MRI) brain scans are commonly acquired in clinical settings to monitor a wide range of neurologica… (see more)l conditions, including neurodegenerative disorders and stroke. While deep learning models have shown promising results analyzing 3D MRI across a number of brain imaging tasks, most are highly tailored for specific tasks with limited labeled data, and are not able to generalize across tasks and/or populations. The development of self-supervised learning (SSL) has enabled the creation of large medical foundation models that leverage diverse, unlabeled datasets ranging from healthy to diseased data, showing significant success in 2D medical imaging applications. However, even the very few foundation models for 3D brain MRI that have been developed remain limited in resolution, scope, or accessibility. In this work, we present a general, high-resolution SimCLR-based SSL foundation model for 3D brain structural MRI, pre-trained on 18,759 patients (44,958 scans) from 11 publicly available datasets spanning diverse neurological diseases. We compare our model to Masked Autoencoders (MAE), as well as two supervised baselines, on four diverse downstream prediction tasks in both in-distribution and out-of-distribution settings. Our fine-tuned SimCLR model outperforms all other models across all tasks. Notably, our model still achieves superior performance when fine-tuned using only 20% of labeled training samples for predicting Alzheimer's disease. We use publicly available code and data, and release our trained model at https://github.com/emilykaczmarek/3D-Neuro-SimCLR, contributing a broadly applicable and accessible foundation model for clinical brain MRI analysis.
2025-09-12
ArXiv (preprint)
doi.org
arxiv.org
SSL-AD: Spatiotemporal Self-Supervised Learning for Generalizability and Adaptability Across Alzheimer's Prediction Tasks and Datasets
Emily Kaczmarek
Justin Szeto
Brennan Nichyporuk
Tal Arbel
Alzheimer's disease is a progressive, neurodegenerative disorder that causes memory loss and cognitive decline. While there has been extensi… (see more)ve research in applying deep learning models to Alzheimer's prediction tasks, these models remain limited by lack of available labeled data, poor generalization across datasets, and inflexibility to varying numbers of input scans and time intervals between scans. In this study, we adapt three state-of-the-art temporal self-supervised learning (SSL) approaches for 3D brain MRI analysis, and add novel extensions designed to handle variable-length inputs and learn robust spatial features. We aggregate four publicly available datasets comprising 3,161 patients for pre-training, and show the performance of our model across multiple Alzheimer's prediction tasks including diagnosis classification, conversion detection, and future conversion prediction. Importantly, our SSL model implemented with temporal order prediction and contrastive learning outperforms supervised learning on six out of seven downstream tasks. It demonstrates adaptability and generalizability across tasks and number of input images with varying time intervals, highlighting its capacity for robust performance across clinical applications. We release our code and model publicly at https://github.com/emilykaczmarek/SSL-AD.
2025-09-12
ArXiv (preprint)
doi.org
arxiv.org
SSL-AD: Spatiotemporal Self-Supervised Learning for Generalizability and Adaptability Across Alzheimer's Prediction Tasks and Datasets
Emily Kaczmarek
Justin Szeto
Brennan Nichyporuk
Tal Arbel
Alzheimer's disease is a progressive, neurodegenerative disorder that causes memory loss and cognitive decline. While there has been extensi… (see more)ve research in applying deep learning models to Alzheimer's prediction tasks, these models remain limited by lack of available labeled data, poor generalization across datasets, and inflexibility to varying numbers of input scans and time intervals between scans. In this study, we adapt three state-of-the-art temporal self-supervised learning (SSL) approaches for 3D brain MRI analysis, and add novel extensions designed to handle variable-length inputs and learn robust spatial features. We aggregate four publicly available datasets comprising 3,161 patients for pre-training, and show the performance of our model across multiple Alzheimer's prediction tasks including diagnosis classification, conversion detection, and future conversion prediction. Importantly, our SSL model implemented with temporal order prediction and contrastive learning outperforms supervised learning on six out of seven downstream tasks. It demonstrates adaptability and generalizability across tasks and number of input images with varying time intervals, highlighting its capacity for robust performance across clinical applications. We release our code and model publicly at https://github.com/emilykaczmarek/SSL-AD.
2025-09-12
ArXiv (preprint)
doi.org
arxiv.org
Fused Lasso Improves Accuracy of Co-occurrence Network Inference in Grouped Samples
Daniel Agyapong
Briana H. Beatty
Peter G. Kennedy
Toby Dylan Hocking
Co-occurrence network inference algorithms have significantly advanced our understanding of microbiome communities. However, these algorithm… (see more)s typically analyze microbial associations within samples collected from a single environmental niche, often capturing only static snapshots rather than dynamic microbial processes. Previous studies have commonly grouped samples from different environmental niches together without fully considering how microbial communities adapt their associations when faced with varying ecological conditions. Our study addresses this limitation by explicitly investigating both spatial and temporal dynamics of microbial communities. We analyzed publicly available microbiome abundance data across multiple locations and time points, to evaluate algorithm performance in predicting microbial associations using our proposed Same-All Cross-validation (SAC) framework. SAC evaluates algorithms in two distinct scenarios: training and testing within the same environmental niche (Same), and training and testing on combined data from multiple environmental niches (All). To overcome the limitations of conventional algorithms, we propose fuser, an algorithm that, while not entirely new in machine learning, is novel for microbiome community network inference. It retains subsample-specific signals while simultaneously sharing relevant information across environments during training. Unlike standard approaches that infer a single generalized network from combined data, fuser generates distinct, environment-specific predictive networks. Our results demonstrate that fuser achieves comparable predictive performance to existing algorithms such as glmnet when evaluated within homogeneous environments (Same), and notably reduces test error compared to baseline algorithms in cross-environment (All) scenarios.
2025-09-11
ArXiv (preprint)
doi.org
arxiv.org
Fused Lasso Improves Accuracy of Co-occurrence Network Inference in Grouped Samples
Daniel Agyapong
Briana H. Beatty
Peter G. Kennedy
Jane C. Marks
Toby Dylan Hocking
Co-occurrence network inference algorithms have significantly advanced our understanding of microbiome communities. However, these algorithm… (see more)s typically analyze microbial associations within samples collected from a single environmental niche, often capturing only static snapshots rather than dynamic microbial processes. Previous studies have commonly grouped samples from different environmental niches together without fully considering how microbial communities adapt their associations when faced with varying ecological conditions. Our study addresses this limitation by explicitly investigating both spatial and temporal dynamics of microbial communities. We analyzed publicly available microbiome abundance data across multiple locations and time points, to evaluate algorithm performance in predicting microbial associations using our proposed Same-All Cross-validation (SAC) framework. SAC evaluates algorithms in two distinct scenarios: training and testing within the same environmental niche (Same), and training and testing on combined data from multiple environmental niches (All). To overcome the limitations of conventional algorithms, we propose fuser, an algorithm that, while not entirely new in machine learning, is novel for microbiome community network inference. It retains subsample-specific signals while simultaneously sharing relevant information across environments during training. Unlike standard approaches that infer a single generalized network from combined data, fuser generates distinct, environment-specific predictive networks. Our results demonstrate that fuser achieves comparable predictive performance to existing algorithms such as glmnet when evaluated within homogeneous environments (Same), and notably reduces test error compared to baseline algorithms in cross-environment (All) scenarios.
2025-09-11
ArXiv (preprint)
doi.org
arxiv.org
OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
Victor Livernoche
Akshatha Arodi
Andreea Musulan
Zachary Yang
Adam Salvail
Ga'etan Marceau Caron
Jean-François Godbout
Reihaneh Rabbany
Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically… (see more) sensitive contexts. This challenge is amplified by the increasing realism of modern generative models, which our human perception study confirms are often indistinguishable from real images. Yet, existing deepfake detection benchmarks rely on outdated generators or narrowly scoped datasets (e.g., single-face imagery), limiting their utility for real-world detection. To address these gaps, we present OpenFake, a large politically grounded dataset specifically crafted for benchmarking against modern generative models with high realism, and designed to remain extensible through an innovative crowdsourced adversarial platform that continually integrates new hard examples. OpenFake comprises nearly four million total images: three million real images paired with descriptive captions and almost one million synthetic counterparts from state-of-the-art proprietary and open-source models. Detectors trained on OpenFake achieve near-perfect in-distribution performance, strong generalization to unseen generators, and high accuracy on a curated in-the-wild social media test set, significantly outperforming models trained on existing datasets. Overall, we demonstrate that with high-quality and continually updated benchmarks, automatic deepfake detection is both feasible and effective in real-world settings.
2025-09-11
ArXiv (preprint)
arxiv.org
arxiv.org
OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
Victor Livernoche
Akshatha Arodi
Andreea Musulan
Zachary Yang
Adam Salvail
Ga'etan Marceau Caron
Jean-François Godbout
Reihaneh Rabbany
Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically… (see more) sensitive contexts. This challenge is amplified by the increasing realism of modern generative models, which our human perception study confirms are often indistinguishable from real images. Yet, existing deepfake detection benchmarks rely on outdated generators or narrowly scoped datasets (e.g., single-face imagery), limiting their utility for real-world detection. To address these gaps, we present OpenFake, a large politically grounded dataset specifically crafted for benchmarking against modern generative models with high realism, and designed to remain extensible through an innovative crowdsourced adversarial platform that continually integrates new hard examples. OpenFake comprises nearly four million total images: three million real images paired with descriptive captions and almost one million synthetic counterparts from state-of-the-art proprietary and open-source models. Detectors trained on OpenFake achieve near-perfect in-distribution performance, strong generalization to unseen generators, and high accuracy on a curated in-the-wild social media test set, significantly outperforming models trained on existing datasets. Overall, we demonstrate that with high-quality and continually updated benchmarks, automatic deepfake detection is both feasible and effective in real-world settings.
2025-09-11
ArXiv (preprint)
arxiv.org
arxiv.org
OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detection
Victor Livernoche
Akshatha Arodi
Andreea Musulan
Zachary Yang
Adam Salvail
Ga'etan Marceau Caron
Jean-François Godbout
Reihaneh Rabbany
Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically… (see more) sensitive contexts. This challenge is amplified by the increasing realism of modern generative models, which our human perception study confirms are often indistinguishable from real images. Yet, existing deepfake detection benchmarks rely on outdated generators or narrowly scoped datasets (e.g., single-face imagery), limiting their utility for real-world detection. To address these gaps, we present OpenFake, a large politically grounded dataset specifically crafted for benchmarking against modern generative models with high realism, and designed to remain extensible through an innovative crowdsourced adversarial platform that continually integrates new hard examples. OpenFake comprises nearly four million total images: three million real images paired with descriptive captions and almost one million synthetic counterparts from state-of-the-art proprietary and open-source models. Detectors trained on OpenFake achieve near-perfect in-distribution performance, strong generalization to unseen generators, and high accuracy on a curated in-the-wild social media test set, significantly outperforming models trained on existing datasets. Overall, we demonstrate that with high-quality and continually updated benchmarks, automatic deepfake detection is both feasible and effective in real-world settings.
2025-09-11
ArXiv (preprint)
doi.org
arxiv.org