Publications

Correction to: The patient advisor, an organizational resource as a lever for an enhanced oncology patient experience (PAROLEonco): a longitudinal multiple case study protocol
M. P. Pomey
M. de Guise
M. Desforges
K. Bouchard
C. Vialaron
L. Normandin
M. Iliescu-Nelea
I. Fortin
I. Ganache
C. Régis
Z. Rosberger
D. Charpentier
L. Bélanger
M. Dorval
D. P. Ghadiri
M. Lavoie-Tremblay
A. Boivin
J. F. Pelletier
N. Fernandez
A. M. Danino
An amendment to this paper has been published and can be accessed via the original article.
2021-01-13
BMC Health Services Research (published)
doi.org
Deep learning identifies partially overlapping subnetworks in the human social brain
Hannah Kiesow
R. Nathan Spreng
Avram J. Holmes
Mallar Chakravarty
Andre Marquand
B.T. Thomas Yeo
Danilo Bzdok
2021-01-13
Communications Biology (published)
doi.org
Systematic detection of brain protein-coding genes under positive selection during primate evolution and their roles in cognition
Guillaume Dumas
Simon Malesys
Thomas Bourgeron
The human brain differs from that of other primates, but the genetic basis of these differences remains unclear. We investigated the evoluti… (see more)onary pressures acting on almost all human protein-coding genes (N = 11,667; 1:1 orthologs in primates) based on their divergence from those of early hominins, such as Neanderthals, and non-human primates. We confirm that genes encoding brain-related proteins are among the most strongly conserved protein-coding genes in the human genome. Combining our evolutionary pressure metrics for the protein-coding genome with recent data sets, we found that this conservation applied to genes functionally associated with the synapse and expressed in brain structures such as the prefrontal cortex and the cerebellum. Conversely, several genes presenting signatures commonly associated with positive selection appear as causing brain diseases or conditions, such as micro/macrocephaly, Joubert syndrome, dyslexia, and autism. Among those, a number of DNA damage response genes associated with microcephaly in humans such as BRCA1, NHEJ1, TOP3A, and RNF168 show strong signs of positive selection and might have played a role in human brain size expansion during primate evolution. We also showed that cerebellum granule neurons express a set of genes also presenting signatures of positive selection and that may have contributed to the emergence of fine motor skills and social cognition in humans. This resource is available online and can be used to estimate evolutionary constraints acting on a set of genes and to explore their relative contributions to human traits.
2021-01-12
Genome Research (published)
doi.org
Adversarial score matching and improved sampling for image generation
Alexia Jolicoeur-Martineau
Rémi Piché-Taillefer
Remi Tachet des Combes
Ioannis Mitliagkas
Denoising Score Matching with Annealed Langevin Sampling (DSM-ALS) has recently found success in generative modeling. The approach works by … (see more)first training a neural network to estimate the score of a distribution, and then using Langevin dynamics to sample from the data distribution assumed by the score network. Despite the convincing visual quality of samples, this method appears to perform worse than Generative Adversarial Networks (GANs) under the Fréchet Inception Distance, a standard metric for generative models. We show that this apparent gap vanishes when denoising the final Langevin samples using the score network. In addition, we propose two improvements to DSM-ALS: 1) Consistent Annealed Sampling as a more stable alternative to Annealed Langevin Sampling, and 2) a hybrid training formulation, composed of both Denoising Score Matching and adversarial objectives. By combining these two techniques and exploring different network architectures, we elevate score matching methods and obtain results competitive with state-of-the-art image generation on CIFAR-10.
2021-01-11
ICLR.cc/2021/Conference (poster)
openreview.net
openreview.net
Batch Reinforcement Learning Through Continuation Method
Yijie Guo
Shengyu Feng
Nicolas Roux
Ed Chi
Honglak Lee
Minmin Chen
Many real-world applications of reinforcement learning (RL) require the agent to learn from a fixed set of trajectories, without collecting … (see more)new interactions. Policy optimization under this setting is extremely challenging as: 1) the geometry of the objective function is hard to optimize efficiently; 2) the shift of data distributions causes high noise in the value estimation. In this work, we propose a simple yet effective policy iteration approach to batch RL using global optimization techniques known as continuation. By constraining the difference between the learned policy and the behavior policy that generates the fixed trajectories, and continuously relaxing the constraint, our method 1) helps the agent escape local optima; 2) reduces the error in policy evaluation in the optimization procedure. We present results on a variety of control tasks, game environments, and a recommendation task to empirically demonstrate the efficacy of our proposed method.
2021-01-11
ICLR.cc/2021/Conference (poster)
openreview.net
openreview.net
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
Jonathan Pilault
Amine El hattami
Christopher Pal
Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MT… (see more)L must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and negative task transfer, or learning interference. Often, in Natural Language Processing (NLP), a separate model per task is needed to obtain the best performance. However, many fine-tuning approaches are both parameter inefficient, i.e., potentially involving one new model per task, and highly susceptible to losing knowledge acquired during pretraining. We propose a novel Transformer based Hypernetwork Adapter consisting of a new conditional attention mechanism as well as a set of task-conditioned modules that facilitate weight sharing. Through this construction, we achieve more efficient parameter sharing and mitigate forgetting by keeping half of the weights of a pretrained model fixed. We also use a new multi-task data sampling strategy to mitigate the negative effects of data imbalance across tasks. Using this approach, we are able to surpass single task fine-tuning methods while being parameter and data efficient (using around 66% of the data). Compared to other BERT Large methods on GLUE, our 8-task model surpasses other Adapter methods by 2.8% and our 24-task model outperforms by 0.7-1.0% models that use MTL and single task fine-tuning. We show that a larger variant of our single multi-task model approach performs competitively across 26 NLP tasks and yields state-of-the-art results on a number of test and development sets.
2021-01-11
ICLR.cc/2021/Conference (poster)
openreview.net
openreview.net
Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
Rishabh Agarwal
Marlos C. Machado
Pablo Samuel Castro
Bellemare Marc-Emmanuel
Reinforcement learning methods trained on few environments rarely learn policies that generalize to unseen environments. To improve generali… (see more)zation, we incorporate the inherent sequential structure in reinforcement learning into the representation learning process. This approach is orthogonal to recent approaches, which rarely exploit this structure explicitly. Specifically, we introduce a theoretically motivated policy similarity metric (PSM) for measuring behavioral similarity between states. PSM assigns high similarity to states for which the optimal policies in those states as well as in future states are similar. We also present a contrastive representation learning procedure to embed any state similarity metric, which we instantiate with PSM to obtain policy similarity embeddings (PSEs). We demonstrate that PSEs improve generalization on diverse benchmarks, including LQR with spurious correlations, a jumping task from pixels, and Distracting DM Control Suite.
2021-01-11
ICLR.cc/2021/Conference (spotlight)
openreview.net
openreview.net
DC3: A learning method for optimization with hard constraints
Priya L. Donti
David Rolnick
J Zico Kolter
Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the… (see more) use of deep networks as cheap"approximate solvers."Unfortunately, naive deep learning approaches typically cannot enforce the hard constraints of such problems, leading to infeasible solutions. In this work, we present Deep Constraint Completion and Correction (DC3), an algorithm to address this challenge. Specifically, this method enforces feasibility via a differentiable procedure, which implicitly completes partial solutions to satisfy equality constraints and unrolls gradient-based corrections to satisfy inequality constraints. We demonstrate the effectiveness of DC3 in both synthetic optimization tasks and the real-world setting of AC optimal power flow, where hard constraints encode the physics of the electrical grid. In both cases, DC3 achieves near-optimal objective values while preserving feasibility.
2021-01-11
ICLR.cc/2021/Conference (poster)
openreview.net
openreview.net
Inherent privacy limitations of decentralized contact tracing apps
Yoshua Bengio
Daphne Ippolito
Richard Janda
Max Jarvie
Benjamin Prud'homme
Jean-François Rousseau
Abhinav Sharma
Yun William Yu
2021-01-11
Journal of the American Medical Informatics Association : JAMIA (published)
doi.org
A Universal Representation Transformer Layer for Few-Shot Image Classification
Li Li
William L. Hamilton
Guodong Long
Jing Jiang
Hugo Larochelle
Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of mult… (see more)i-domain few-shot image classification, where unseen classes and examples come from diverse data sources. This problem has seen growing interest and has inspired the development of benchmarks such as Meta-Dataset. A key challenge in this multi-domain setting is to effectively integrate the feature representations from the diverse set of training domains. Here, we propose a Universal Representation Transformer (URT) layer, that meta-learns to leverage universal features for few-shot classification by dynamically re-weighting and composing the most appropriate domain-specific representations. In experiments, we show that URT sets a new state-of-the-art result on Meta-Dataset. Specifically, it achieves top-performance on the highest number of data sources compared to competing methods. We analyze variants of URT and present a visualization of the attention score heatmaps that sheds light on how the model performs cross-domain generalization.
2021-01-11
ICLR.cc/2021/Conference (poster)
openreview.net
openreview.net
Mass‐spectrometry analysis of the human pineal proteome during night and day and in autism
Guillaume Dumas
Hany Goubran‐Botros
Mariette Matondo
Cécile Pagan
Cyril Boulègue
Thibault Chaze
Julia Chamot‐Rooke
Erik Maronde
Thomas Bourgeron
The human pineal gland regulates day‐night dynamics of multiple physiological processes, especially through the secretion of melatonin. Us… (see more)ing mass‐spectrometry‐based proteomics and dedicated analysis tools, we identify proteins in the human pineal gland and analyze systematically their variation throughout the day and compare these changes in the pineal proteome between control specimens and donors diagnosed with autism. Results reveal diverse regulated clusters of proteins with, among others, catabolic carbohydrate process and cytoplasmic membrane‐bounded vesicle‐related proteins differing between day and night and/or control versus autism pineal glands. These data show novel and unexpected processes happening in the human pineal gland during the day/night rhythm as well as specific differences between autism donor pineal glands and those from controls.
2021-01-10
Journal of Pineal Research (published)
doi.org
Attention Based Pruning for Shift Networks
Ghouthi Boukli hacene
Carlos Lassance
Vincent Gripon
Matthieu Courbariaux
Yoshua Bengio
In many application domains such as computer vision, Convolutional Layers (CLs) are key to the accuracy of deep learning methods. However, i… (see more)t is often required to assemble a large number of CLs, each containing thousands of parameters, in order to reach state-of-the-art accuracy, thus resulting in complex and demanding systems that are poorly fitted to resource-limited devices. Recently, methods have been proposed to replace the generic convolution operator by the combination of a shift operation and a simpler 1x1 convolution. The resulting block, called Shift Layer (SL), is an efficient alternative to CLs in the sense it allows to reach similar accuracies on various tasks with faster computations and fewer parameters. In this contribution, we introduce Shift Attention Layers (SALs), which extend SLs by using an attention mechanism that learns which shifts are the best at the same time the network function is trained. We demonstrate SALs are able to outperform vanilla SLs (and CLs) on various object recognition benchmarks while significantly reducing the number of float operations and parameters for the inference.
2021-01-09
International Conference on Pattern Recognition (published)
doi.org
arxiv.org