Publications

Assessing the potential for virtualizable care in the pediatric emergency department
Esli Osmanlliu
Brett Burstein
Robyn Tamblyn
David L Buckeridge
There is a high potential for patient-to-provider telemedicine in the PED setting. Local patient and visit-level characteristics must be con… (voir plus)sidered in the design of safe and inclusive telemedicine models for pediatric acute care.
2022-11-19
Journal of Telemedicine and Telecare (publié)
doi.org
Does Entity Abstraction Help Generative Transformers Reason?
Nicolas Gontier
Siva Reddy
Christopher Pal
We study the utility of incorporating entity type abstractions into pre-trained Transformers and test these methods on four NLP tasks requir… (voir plus)ing different forms of logical reasoning: (1) compositional language understanding with text-based relational reasoning (CLUTRR), (2) abductive reasoning (ProofWriter), (3) multi-hop question answering (HotpotQA), and (4) conversational question answering (CoQA). We propose and empirically explore three ways to add such abstraction: (i) as additional input embeddings, (ii) as a separate sequence to encode, and (iii) as an auxiliary prediction task for the model. Overall, our analysis demonstrates that models with abstract entity knowledge performs better than without it. The best abstraction aware models achieved an overall accuracy of 88.8% and 91.8% compared to the baseline model achieving 62.9% and 89.8% on CLUTRR and ProofWriter respectively. However, for HotpotQA and CoQA, we find that F1 scores improve by only 0.5% on average. Our results suggest that the benefit of explicit abstraction is significant in formally defined logical reasoning settings requiring many reasoning hops, but point to the notion that it is less beneficial for NLP tasks having less formal logical structure.
2022-11-19
TMLR (accepté)
openreview.net
openreview.net
Learning from uncertain concepts via test time interventions
Ivaxi Sheth
Aamer Abdul Rahman
Laya Rafiee Sevyeri
Mohammad Havaei
S Ebrahimi Kahou
With neural networks applied to safety-critical applications, it has become increasingly important to understand the defining features of de… (voir plus)cision-making. Therefore, the need to uncover the black boxes to rational representational space of these neural networks is apparent. Concept bottleneck model (CBM) encourages interpretability by predicting human-understandable concepts. They predict concepts from input images and then labels from concepts. Test time intervention, a salient feature of CBM, allows for human-model interactions. However, these interactions are prone to information leakage and can often be ineffective inappropriate communication with humans. We propose a novel uncertainty based strategy, \emph{SIUL: Single Interventional Uncertainty Learning} to select the interventions. Additionally, we empirically test the robustness of CBM and the effect of SIUL interventions under adversarial attack and distributional shift. Using SIUL, we observe that the interventions suggested lead to meaningful corrections along with mitigation of concept leakage. Extensive experiments on three vision datasets along with a histopathology dataset validate the effectiveness of our interventional learning.
2022-11-19
NeurIPS.cc/2022/Workshop/TSRML (accepté)
openreview.net
openreview.net
Striving for data-model efficiency: Identifying data externalities on group performance
Esther Rolf
Ben Packer
Alex Beutel
Fernando Diaz
2022-11-19
NeurIPS.cc/2022/Workshop/TSRML (accepté)
doi.org
openreview.net
GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction
Dominic Masters
Josef Dean
Kerstin Klaser
Zhiyi Li
Samuel Maddrell-Mander
Adam Sanders
Hatem Helal
Deniz Beker
Ladislav Rampasek
Dominique Beaini
2022-11-17
ArXiv (prépublication)
doi.org
arxiv.org
SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness
Goncalo Mordido
Sébastien Henwood
A. Chandar
Franccois Leduc-Primeau
Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitig… (voir plus)ate such degradation, existing methods typically add perturbations to the DNN weights during training to simulate inference on noisy hardware. However, this often requires knowledge about the target hardware and leads to a trade-off between DNN performance and robustness, decreasing the former to increase the latter. In this work, we show that applying sharpness-aware training, by optimizing for both the loss value and loss sharpness, significantly improves robustness to noisy hardware at inference time without relying on any assumptions about the target hardware. In particular, we propose a new adaptive sharpness-aware method that conditions the worst-case perturbation of a given weight not only on its magnitude but also on the range of the weight distribution. This is achieved by performing sharpness-aware minimization scaled by outlier minimization (SAMSON). Our approach outperforms existing sharpness-aware training methods both in terms of model generalization performance in noiseless regimes and robustness in noisy settings, as measured on several architectures and datasets.
2022-11-17
ArXiv (prépublication)
arxiv.org
arxiv.org
APP: Anytime Progressive Pruning
Diganta Misra
Bharat Runwal
Tianlong Chen
Zhangyang Wang
Irina Rish
With the latest advances in deep learning, several methods have been investigated for optimal learning settings in scenarios where the data … (voir plus)stream is continuous over time. However, training sparse networks in such settings has often been overlooked. In this paper, we explore the problem of training a neural network with a target sparsity in a particular case of online learning: the anytime learning at macroscale paradigm (ALMA). We propose a novel way of progressive pruning, referred to as \textit{Anytime Progressive Pruning} (APP); the proposed approach significantly outperforms the baseline dense and Anytime OSP models across multiple architectures and datasets under short, moderate, and long-sequence training. Our method, for example, shows an improvement in accuracy of
2022-11-16
ACML.org/2022/Workshop/CLL (accepté)
doi.org
openreview.net
The Liver Tumor Segmentation Benchmark (LiTS)
Patrick Bilic
Patrick Christ
Eugene Vorontsov
Hongwei Bran Li
Grzegorz Chlebus
Hao Chen
Qi Dou
Chi-Wing Fu
Xu Han
Gabriel Efrain Humpire Mamani
Pheng Ann Heng
Jürgen Hesser
Samuel Kadoury
Julian Walter Holch
Tomasz Konopczynski
Miao Yue
Chunming Li
X. Li
Jana Lipková
John Lowengrub … (voir 99 de plus)
Michal Marianne Amitai
Hans Meine
J. Moltz
Christopher Pal
Marie Piraud
Ivan Ezhov
Xiaojuan Qi
Fernando Navarro
Jin Qi
Florian Kofler
Markus Rempfler
Johannes C. Paetzold
Karsten Roth
Suprosanna Shit
Andrea Schenk
Xiaobin Hu
Anjany Sekuboyina
Ping Zhou
Christian Hülsemeyer
Marcel Beetz
Jan Kirschke
Florian Ettlinger
Felix Gruen
Benedikt Wiestler
Zhiheng Zhang
Georgios Kaissis
Fabian Lohöfer
Rickmer Braren
J. Holch
Michela Antonelli
Felix Hofmann
Woong Bae
Wieland Sommer
Míriam Bellver
Volker Heinemann
Lei Bi
Colin Jacobs
G. Mamani
Bram van Ginneken
Erik B. Dam
Gabriel Chartrand
An Tang
Michal Drozdzal
Bogdan Georgescu
Avi Ben-Cohen
Xavier Giró-i-Nieto
Eyal Klang
M. Amitai
E. Konen
Hayit Greenspan
Johan Moreau
Jan Hendrik Moltz
Alexandre Hostettler
Christian Igel
Luc Soler
Fabian Isensee
Refael Vivanti
Paul Jäger
Adi Szeskin
Fucang Jia
Naama Lev-Cohain
Krishna Chaitanya Kaluva
Jacob Sosna
Mahendra Khened
Leo Joskowicz
Ildoo Kim
Bjoern Menze
Jae-Hun Kim
Zengming Shen
Sungwoong Kim
Simon Kohl
Avinash Kori
Ganapathy Krishnamurthi
Fan Li
Hongchao Li
Junbo Li
Xiaomeng Li
Jun Ma
Klaus Maier-Hein
Kevis-Kokitsi Maninis
Dorit Merhof
Akshay Pai
Mathias Perslev
Jens Petersen
Jordi Pont-Tuset
Oliver Rippel
Ignacio Sarasua
Jordi Torres
Christian Wachinger
Chunliang Wang
Leon Weninger
Jianrong Wu
Daguang Xu
Xiaoping Yang
Simon Chun-Ho Yu
Yading Yuan
Liping Zhang
Jorge Cardoso
Spyridon Bakas
2022-11-16
Medical image analysis (publié)
doi.org
arxiv.org
Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors
Anjun Hu
Jean-Pierre R. Falet
Brennan Nichyporuk
Changjian Shui
Douglas Arnold
Sotirios A. Tsaftaris
Tal Arbel
We propose a hierarchically structured variational inference model for accurately disentangling observable evidence of disease (e.g. brain l… (voir plus)esions or atrophy) from subject-specific anatomy in brain MRIs. With flexible, partially autoregressive priors, our model (1) addresses the subtle and fine-grained dependencies that typically exist between anatomical and pathological generating factors of an MRI to ensure the clinical validity of generated samples; (2) preserves and disentangles finer pathological details pertaining to a patient's disease state. Additionally, we experiment with an alternative training configuration where we provide supervision to a subset of latent units. It is shown that (1) a partially supervised latent space achieves a higher degree of disentanglement between evidence of disease and subject-specific anatomy; (2) when the prior is formulated with an autoregressive structure, knowledge from the supervision can propagate to the unsupervised latent units, resulting in more informative latent representations capable of modelling anatomy-pathology interdependencies.
2022-11-14
ArXiv (prépublication)
doi.org
arxiv.org
Identification of Novel Cell Surface Therapeutic Targets for KMT2A-Rearranged Acute Myeloid Leukemia
Louis Theret
Marie-Eve Bordeleau
Azadeh Hajmirza
Arnaud Metois
Ossama Moujaber
Éric Audemard
Jean-François Spinella
Jalila Chagraoui
Léo Aubert
Azer Farah
Véronique Lisi
Éric Bonneil
Isabel Boivin
Nadine Mayotte
Tara MacRae
Pierre Thibault
Sébastien Lemieux
Vincent-Philippe Lavallee
Josée Hébert
Guy Sauvageau … (voir 1 de plus)
Philippe P Roux
2022-11-14
Blood (publié)
doi.org
IL1R1 Expression Predicts the Benefit from Allogeneic Hematopoietic Stem Cell Transplantation in Patients with Acute Myeloid Leukemia and Intermediate-Risk Cytogenetics
Guillaume Richard-Carpentier
Francois Beliveau
Sandrine Lacoste
Jean-François Spinella
Michael Vladovsky
Patrick Gendron
Sébastien Lemieux
Vincent-Philippe Lavallee
Guy Sauvageau
Josée Hébert
2022-11-14
Blood (publié)
doi.org
Targeting PLZF Enhances Glucocorticoid Sensitivity in Acute Myeloid Leukemia
Azadeh Hajmirza
Laura Simon
Jalila Chagraoui
Nadine Mayotte
Jean-François Spinella
Tara MacRae
Bernhard Lehnertz
Thierry Bertomeu
Jasmin Coulombe-Huntington
Geneviève Boucher
Sébastien Lemieux
Mike Tyers
Josée Hébert
Guy Sauvageau
2022-11-14
Blood (publié)
doi.org