Publications

Fast Heterogeneous Task Mapping for Reducing Edge DNN Latency
M. L. Kornelsen
S. H. Mozafari
J. J. Clark
B. H. Meyer
W. J. Gross
To meet DNN inference latency constraints on resource-constrained edge devices, we employ heterogeneous computing, utilizing multiple proces… (see more)sing elements (e.g. CPU + GPU) accelerate inference. This leads to the challenge of efficiently mapping DNN operations to heterogeneous processing elements. For this task, we introduce a novel genetic algorithm (GA) optimizer. Through intelligent initialization and a customized mutation operation, we are able to evaluate 20x fewer generations while finding superior configurations compared with a baseline GA. Using our mapping optimizer, we find device placement configurations that achieve 15%, 24%, and 31% inference speed-up for BERT, SqueezeBERT, and InceptionV3,respectively.
2022-06-30
IEEE International Conference on Application-Specific Systems, Architectures, and Processors (published)
doi.org
IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control
François-Xavier Devailly
Denis Larocque
Laurent Charlin
Scaling adaptive traffic signal control involves dealing with combinatorial state and action spaces. Multi-agent reinforcement learning atte… (see more)mpts to address this challenge by distributing control to specialized agents. However, specialization hinders generalization and transferability, and the computational graphs underlying neural-network architectures—dominating in the multi-agent setting—do not offer the flexibility to handle an arbitrary number of entities which changes both between road networks, and over time as vehicles traverse the network. We introduce Inductive Graph Reinforcement Learning (IG-RL) based on graph-convolutional networks which adapts to the structure of any road network, to learn detailed representations of traffic signal controllers and their surroundings. Our decentralized approach enables learning of a transferable-adaptive-traffic-signal-control policy. After being trained on an arbitrary set of road networks, our model can generalize to new road networks and traffic distributions, with no additional training and a constant number of parameters, enabling greater scalability compared to prior methods. Furthermore, our approach can exploit the granularity of available data by capturing the (dynamic) demand at both the lane level and the vehicle level. The proposed method is tested on both road networks and traffic settings never experienced during training. We compare IG-RL to multi-agent reinforcement learning and domain-specific baselines. In both synthetic road networks and in a larger experiment involving the control of the 3,971 traffic signals of Manhattan, we show that different instantiations of IG-RL outperform baselines.
2022-06-30
IEEE Transactions on Intelligent Transportation Systems (published)
doi.org
arxiv.org
Leishmania parasites exchange drug-resistance genes through extracellular vesicles
Noélie Douanne
George Dong
Atia Amin
Lorena Bernardo
Mathieu Blanchette
David Langlais
Martin Olivier
Christopher Fernandez-Prada
2022-06-30
Cell Reports (published)
doi.org
Naming Autism in the Right Context
Andres Roman-Urrestarazu
Guillaume Dumas
Varun Warrier
2022-06-30
JAMA Pediatrics (published)
doi.org
The application of artificial intelligence to biology and neuroscience
Blake Richards
Doris Tsao
Anthony Zador
2022-06-30
Cell (published)
doi.org
Understanding Generalization via Leave-One-Out Conditional Mutual Information
MAHDI HAGHIFAM
Shay Moran
Daniel M. Roy
Gintare Karolina Dziugaite
2022-06-30
2022 IEEE International Symposium on Information Theory (ISIT) (published)
doi.org
arxiv.org
R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS
Kyle Kastner
Aaron Courville
2022-06-29
ArXiv (preprint)
doi.org
arxiv.org
A guided multiverse study of neuroimaging analyses
Jessica Dafflon
Pedro F. da Costa
František Váša
Ricardo Pio Monti
Danilo Bzdok
Peter J. Hellyer
Federico Turkheimer
Jonathan Smallwood
Emily Jones
Robert Leech
For most neuroimaging questions the range of possible analytic choices makes it unclear how to evaluate conclusions from any single analytic… (see more) method. One possible way to address this issue is to evaluate all possible analyses using a multiverse approach, however, this can be computationally challenging and sequential analyses on the same data can compromise predictive power. Here, we establish how active learning on a low-dimensional space capturing the inter-relationships between pipelines can efficiently approximate the full spectrum of analyses. This approach balances the benefits of a multiverse analysis without incurring the cost on computational and predictive power. We illustrate this approach with two functional MRI datasets (predicting brain age and autism diagnosis) demonstrating how a multiverse of analyses can be efficiently navigated and mapped out using active learning. Furthermore, our presented approach not only identifies the subset of analysis techniques that are best able to predict age or classify individuals with autism spectrum disorder and healthy controls, but it also allows the relationships between analyses to be quantified.
2022-06-28
Nature Communications (published)
doi.org
Integrating Equity, Diversity, and Inclusion throughout the lifecycle of Artificial Intelligence in health
Milka Nyariro
Elham Emami
Samira Abbasgholizadeh Rahimi
2022-06-28
13th Augmented Human International Conference (published)
doi.org
Reproducible between-person brain-behavior associations do not always require thousands of individuals
Colin G. DeYoung
Tyler A. Sassenberg
Rany Abend
Timothy A. Allen
Roger E. Beaty
Mark A. Bellgrove
Scott D. Blain
Danilo Bzdok
Robert S. Chavez
Stephen A. Engel
Ma Feilong
Alex Fornito
Erhan Genç
Vina M. Goghari
Rachael Grazioplene
Jamie L. Hanson
James V. Haxby
Kirsten Hilger
Philipp Homan
Keanan J. Joyner … (see 12 more)
Antonia N. Kaczkurkin
Robert D. Latzman
Elizabeth A. Martin
Luca Passamonti
Alan D. Pickering
Adam Safron
Michelle N. Servaas
Luke D. Smillie
R. Nathan Spreng
Jeggan Tiego
Essi Viding
Jan Wacker
Marek et al. analyzed three very large magnetic resonance imaging (MRI) datasets and concluded that thousands of participants are necessary … (see more)to ensure replicable results in “brain-wide associations studies,” which they defined as “studies of the associations between common inter-individual variability in human brain structure/function and cognition or psychiatric symptomatology.” This conclusion overgeneralizes the implications of their findings and is likely to have an unwarranted chilling effect on neuroimaging research focused on individual differences, preventing good research with samples in the hundreds from being funded and conducted. To fend off these negative consequences, we explain why their conclusion is not fully justified, discuss methods that can yield larger effects, and suggest practical guidelines for sample size, recognizing the potential utility of samples in the hundreds.
2022-06-28
PsyArXiv Preprints (preprint)
doi.org
Annotation Cost-Sensitive Deep Active Learning with Limited Data (Student Abstract)
Renaud Bernatchez
Audrey Durand
Flavie Lavoie-Cardinal
2022-06-27
Proceedings of the AAAI Conference on Artificial Intelligence (published)
doi.org
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
Sébastien Lachapelle
Pau Rodríguez
Yash Sharma
Katie E Everett
Rémi Le Priol
Alexandre Lacoste
Simon Lacoste-Julien
This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent f… (see more)actors of interest depend sparsely on past latent factors and/or observed auxiliary variables. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that relates them. We develop a rigorous identifiability theory, building on recent nonlinear independent component analysis (ICA) results, that formalizes this principle and shows how the latent variables can be recovered up to permutation if one regularizes the latent mechanisms to be sparse and if some graph connectivity criterion is satisfied by the data generating process. As a special case of our framework, we show how one can leverage unknown-target interventions on the latent factors to disentangle them, thereby drawing further connections between ICA and causality. We propose a VAE-based method in which the latent mechanisms are learned and regularized via binary masks, and validate our theory by showing it learns disentangled representations in simulations.
2022-06-27
Proceedings of the First Conference on Causal Learning and Reasoning (published)
proceedings.mlr.press
proceedings.mlr.press