Publications

Technical Note—Risk-Averse Regret Minimization in Multistage Stochastic Programs
Mehran Poursoltani
Erick Delage
Angelos Georghiou
2023-01-29
Operational Research (published)
doi.org
Leveraging the Third Dimension in Contrastive Learning
Sumukh K Aithal
Anirudh Goyal
Alex Lamb
Yoshua Bengio
Michael Curtis Mozer
Self-Supervised Learning (SSL) methods operate on unlabeled data to learn robust representations useful for downstream tasks. Most SSL metho… (see more)ds rely on augmentations obtained by transforming the 2D image pixel map. These augmentations ignore the fact that biological vision takes place in an immersive three-dimensional, temporally contiguous environment, and that low-level biological vision relies heavily on depth cues. Using a signal provided by a pretrained state-of-the-art monocular RGB-to-depth model (the \emph{Depth Prediction Transformer}, Ranftl et al., 2021), we explore two distinct approaches to incorporating depth signals into the SSL framework. First, we evaluate contrastive learning using an RGB+depth input representation. Second, we use the depth signal to generate novel views from slightly different camera positions, thereby producing a 3D augmentation for contrastive learning. We evaluate these two approaches on three different SSL methods -- BYOL, SimSiam, and SwAV -- using ImageNette (10 class subset of ImageNet), ImageNet-100 and ImageNet-1k datasets. We find that both approaches to incorporating depth signals improve the robustness and generalization of the baseline SSL methods, though the first approach (with depth-channel concatenation) is superior. For instance, BYOL with the additional depth channel leads to an increase in downstream classification accuracy from 85.3\% to 88.0\% on ImageNette and 84.1\% to 87.0\% on ImageNet-C.
2023-01-26
ArXiv (preprint)
doi.org
openreview.net
Accompanying patients in clinical oncology teams: Reported activities and perceived effects
Marie‐Pascale Pomey
Jesseca Paquette
Monica Iliescu‐Nelea
Cécile Vialaron
Rim Mourad
Karine Bouchard
Louise Normandin
Marie‐Andrée Côté
Mado Desforges
Pénélope Pomey‐Carpentier
Israël Fortin
Isabelle Ganache
Catherine Régis
Zeev Rosberger
Danielle Charpentier
Lynda Bélanger
Michel Dorval
Djahanchah P. Ghadiri
Mélanie Lavoie‐Tremblay
Antoine Boivin … (see 4 more)
Jean‐François Pelletier
Nicolas Fernandez
Alain M. Danino
Michèle de Guise
Two patient–researchers have contributed to the study design, the conduct of the study, the data analysis and interpretation, as well as i… (see more)n the preparation and writing of this manuscript.
2023-01-25
Health Expectations (published)
doi.org
Semi-Supervised Object Detection for Agriculture
Gabriel Tseng
Krisztina Sinkovics
Tom Watsham
David Rolnick
Thomas C. Walters
2023-01-25
AAAI.org/2023/Workshop/AIAFS (poster)
openreview.net
openreview.net
Enhancing Medical Image Segmentation with TransCeption: A Multi-Scale Feature Fusion Approach
Reza Azad
Yiwei Jia
Ehsan Khodapanah Aghdam
Julien Cohen-Adad
Dorit Merhof
While CNN-based methods have been the cornerstone of medical image segmentation due to their promising performance and robustness, they suff… (see more)er from limitations in capturing long-range dependencies. Transformer-based approaches are currently prevailing since they enlarge the reception field to model global contextual correlation. To further extract rich representations, some extensions of the U-Net employ multi-scale feature extraction and fusion modules and obtain improved performance. Inspired by this idea, we propose TransCeption for medical image segmentation, a pure transformer-based U-shape network featured by incorporating the inception-like module into the encoder and adopting a contextual bridge for better feature fusion. The design proposed in this work is based on three core principles: (1) The patch merging module in the encoder is redesigned with ResInception Patch Merging (RIPM). Multi-branch transformer (MB transformer) adopts the same number of branches as the outputs of RIPM. Combining the two modules enables the model to capture a multi-scale representation within a single stage. (2) We construct an Intra-stage Feature Fusion (IFF) module following the MB transformer to enhance the aggregation of feature maps from all the branches and particularly focus on the interaction between the different channels of all the scales. (3) In contrast to a bridge that only contains token-wise self-attention, we propose a Dual Transformer Bridge that also includes channel-wise self-attention to exploit correlations between scales at different stages from a dual perspective. Extensive experiments on multi-organ and skin lesion segmentation tasks present the superior performance of TransCeption compared to previous work. The code is publicly available at https://github.com/mindflow-institue/TransCeption.
2023-01-24
ArXiv (preprint)
doi.org
arxiv.org
Explainable Machine Learning Model to Predict COVID-19 Severity Among Older Adults in the Province of Quebec.
S. A. Rahimi
Charlene H Chu
Roland M. Grad
Mark Karanofsky
Mylene Arsenault
Charlene Esteban Ronquillo
Isabelle Vedel
K. McGilton
Machelle Wilchesky
Context: Patients over the age of 65 years are more likely to experience higher severity and mortality rates than other populations from COV… (see more)ID-19. Clinicians need assistance in supporting their decisions regarding the management of these patients. Artificial Intelligence (AI) can help with this regard. However, the lack of explainability-defined as "the ability to understand and evaluate the internal mechanism of the algorithm/computational process in human terms"-of AI is one of the major challenges to its application in health care. We know little about application of explainable AI (XAI) in health care. Objective: In this study, we aimed to evaluate the feasibility of the development of explainable machine learning models to predict COVID-19 severity among older adults. Design: Quantitative machine learning methods. Setting: Long-term care facilities within the province of Quebec. Participants: Patients 65 years and older presented to the hospitals who had a positive polymerase chain reaction test for COVID-19. Intervention: We used XAI-specific methods (e.g., EBM), machine learning methods (i.e., random forest, deep forest, and XGBoost), as well as explainable approaches such as LIME, SHAP, PIMP, and anchor with the mentioned machine learning methods. Outcome measures: Classification accuracy and area under the receiver operating characteristic curve (AUC). Results: The age distribution of the patients (n=986, 54.6% male) was 84.5□19.5 years. The best-performing models (and their performance) were as follows. Deep forest using XAI agnostic methods LIME (97.36% AUC, 91.65 ACC), Anchor (97.36% AUC, 91.65 ACC), and PIMP (96.93% AUC, 91.65 ACC). We found alignment with the identified reasoning of our models' predictions and clinical studies' findings-about the correlation of different variables such as diabetes and dementia, and the severity of COVID-19 in this population. Conclusions: The use of explainable machine learning models, to predict the severity of COVID-19 among older adults is feasible. We obtained a high-performance level as well as explainability in the prediction of COVID-19 severity in this population. Further studies are required to integrate these models into a decision support system to facilitate the management of diseases such as COVID-19 for (primary) health care providers and evaluate their usability among them.
2023-01-23
Big data (published)
doi.org
Regeneration Learning: A Learning Paradigm for Data Generation
Xu Tan
Tao Qin
Jiang Bian
Tie-Yan Liu
Yoshua Bengio
2023-01-20
ArXiv (preprint)
doi.org
arxiv.org
Robustness and Sample Complexity of Model-Based MARL for General-Sum Markov Games
Jayakumar Subramanian
Amit Sinha
Aditya Mahajan
2023-01-20
Dynamic Games and Applications (published)
doi.org
arxiv.org
Disentangling poststroke cognitive deficits and their neuroanatomical correlates through combined multivariable and multioutcome lesion‐symptom mapping
Nick A. Weaver
Muhammad Hasnain Mamdani
Jae‐Sung Lim
Johannes Matthijs Biesbroek
Geert Jan Biessels
Irene M. C. Huenges Wajer
Yeonwook Kang
Beom Joon Kim
Byung‐Chul Lee
Keon‐Joo Lee
Kyung‐Ho Yu
Hee‐Joon Bae
Danilo Bzdok
Hugo J. Kuijf
Studies in patients with brain lesions play a fundamental role in unraveling the brain's functional anatomy. Lesion‐symptom mapping (LSM) … (see more)techniques can relate lesion location to cognitive performance. However, a limitation of current LSM approaches is that they can only evaluate one cognitive outcome at a time, without considering interdependencies between different cognitive tests. To overcome this challenge, we implemented canonical correlation analysis (CCA) as combined multivariable and multioutcome LSM approach. We performed a proof‐of‐concept study on 1075 patients with acute ischemic stroke to explore whether addition of CCA to a multivariable single‐outcome LSM approach (support vector regression) could identify infarct locations associated with deficits in three well‐defined verbal memory functions (encoding, consolidation, retrieval) based on four verbal memory subscores derived from the Seoul Verbal Learning Test (immediate recall, delayed recall, recognition, learning ability). We evaluated whether CCA could extract cognitive score patterns that matched prior knowledge of these verbal memory functions, and if these patterns could be linked to more specific infarct locations than through single‐outcome LSM alone. Two of the canonical modes identified with CCA showed distinct cognitive patterns that matched prior knowledge on encoding and consolidation. In addition, CCA revealed that each canonical mode was linked to a distinct infarct pattern, while with multivariable single‐outcome LSM individual verbal memory subscores were associated with largely overlapping patterns. In conclusion, our findings demonstrate that CCA can complement single‐outcome LSM techniques to help disentangle cognitive functions and their neuroanatomical correlates.
2023-01-19
Human Brain Mapping (published)
doi.org
lo-fi: distributed fine-tuning without communication
Mitchell Wortsman
Suchin Gururangan
Shen Li
Ali Farhadi
Ludwig Schmidt
Michael G. Rabbat
Ari S. Morcos
When fine-tuning large neural networks, it is common to use multiple nodes and to communicate gradients at each optimization step. By contra… (see more)st, we investigate completely local fine-tuning, which we refer to as lo-fi. During lo-fi, each node fine-tunes independently without any communication. Then, the weights are averaged across nodes at the conclusion of fine-tuning. When fine-tuning DeiT-base and DeiT-large on ImageNet, this procedure matches accuracy in-distribution and improves accuracy under distribution shift compared to the baseline, which observes the same amount of data but communicates gradients at each step. We also observe that lo-fi matches the baseline's performance when fine-tuning OPT language models (up to 1.3B parameters) on Common Crawl. By removing the communication requirement, lo-fi reduces resource barriers for fine-tuning large models and enables fine-tuning in settings with prohibitive communication cost.
2023-01-19
TMLR (accepted)
doi.org
openreview.net
A Framework for Obtaining Accurate Posteriors of Strong Gravitational Lensing Parameters with Flexible Priors and Implicit Likelihoods using Density Estimation
Ronan Legin
Yashar Hezaveh
Laurence Perreault-Levasseur
Benjamin Wandelt
We report the application of implicit likelihood inference to the prediction of the macro-parameters of strong lensing systems with neural n… (see more)etworks. This allows us to perform deep learning analysis of lensing systems within a well-defined Bayesian statistical framework to explicitly impose desired priors on lensing variables, to obtain accurate posteriors, and to guarantee convergence to the optimal posterior in the limit of perfect performance. We train neural networks to perform a regression task to produce point estimates of lensing parameters. We then interpret these estimates as compressed statistics in our inference setup and model their likelihood function using mixture density networks. We compare our results with those of approximate Bayesian neural networks, discuss their significance, and point to future directions. Based on a test set of 100,000 strong lensing simulations, our amortized model produces accurate posteriors for any arbitrary confidence interval, with a maximum percentage deviation of
2023-01-18
The Astrophysical Journal (published)
doi.org
arxiv.org
Label fusion and training methods for reliable representation of inter-rater uncertainty
Andréanne Lemay
Charley Gros
Julien Cohen-Adad
Enamundram Naga Karthik
Medical tasks are prone to inter-rater variability due to multiple factors such as image quality, professional experience and training, or g… (see more)uideline clarity. Training deep learning networks with annotations from multiple raters is a common practice that mitigates the model's bias towards a single expert. Reliable models generating calibrated outputs and reflecting the inter-rater disagreement are key to the integration of artificial intelligence in clinical practice. Various methods exist to take into account different expert labels. We focus on comparing three label fusion methods: STAPLE, average of the rater's segmentation, and random sampling of each rater's segmentation during training. Each label fusion method is studied using both the conventional training framework and the recently published SoftSeg framework that limits information loss by treating the segmentation task as a regression. Our results, across 10 data splittings on two public datasets, indicate that SoftSeg models, regardless of the ground truth fusion method, had better calibration and preservation of the inter-rater rater variability compared with their conventional counterparts without impacting the segmentation performance. Conventional models, i.e., trained with a Dice loss, with binary inputs, and sigmoid/softmax final activate, were overconfident and underestimated the uncertainty associated with inter-rater variability. Conversely, fusing labels by averaging with the SoftSeg framework led to underconfident outputs and overestimation of the rater disagreement. In terms of segmentation performance, the best label fusion method was different for the two datasets studied, indicating this parameter might be task-dependent. However, SoftSeg had segmentation performance systematically superior or equal to the conventionally trained models and had the best calibration and preservation of the inter-rater variability.
2023-01-17
Machine Learning for Biomedical Imaging (published)
doi.org
arxiv.org