Publications

From IID to the Independent Mechanisms assumption in continual learning
Oleksiy Ostapenko
Pau Rodríguez
Alexandre Lacoste
Laurent Charlin
2023-06-03
Proceedings of The First AAAI Bridge Program on Continual Causality (published)
proceedings.mlr.press
proceedings.mlr.press
Self-Supervised Learning for Infant Cry Analysis
Arsenii Gorin
Yusuf Cem Sübakan
Sajjad Abdoli
Junhao Wang
Samantha Latremouille
Charles Onu
In this paper, we explore self-supervised learning (SSL) for analyzing a first-of-its-kind database of cry recordings containing clinical in… (see more)dications of more than a thousand newborns. Specifically, we target cry-based detection of neurological injury as well as identification of cry triggers such as pain, hunger, and discomfort. Annotating a large database in the medical setting is expensive and timeconsuming, typically requiring the collaboration of several experts over years. Leveraging large amounts of unlabeled audio data to learn useful representations can lower the cost of building robust models and, ultimately, clinical solutions. In this work, we experiment with self-supervised pre-training of a convolutional neural network on large audio datasets. We show that pre-training with SSL contrastive loss (SimCLR) performs significantly better than supervised pre-training for both neuro injury and cry triggers. In addition, we demonstrate further performance gains through SSL-based domain adaptation using unlabeled infant cries. We also show that using such SSL-based pre-training for adaptation to cry sounds decreases the need for labeled data of the overall system.
2023-06-03
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (published)
doi.org
arxiv.org
ANSEL Photobot: A Robot Event Photographer with Semantic Intelligence
Dmitriy Rivkin
Gregory Dudek
Nikhil Kakodkar
David Meger
Oliver Limoyo
Xue Liu
Francois Hogan
Our work examines the way in which large language models can be used for robotic planning and sampling, specifically the context of automate… (see more)d photographic documentation. Specifically, we illustrate how to produce a photo-taking robot with an exceptional level of semantic awareness by leveraging recent advances in general purpose language (LM) and vision-language (VLM) models. Given a high-level description of an event we use an LM to generate a natural-language list of photo descriptions that one would expect a photographer to capture at the event. We then use a VLM to identify the best matches to these descriptions in the robot's video stream. The photo portfolios generated by our method are consistently rated as more appropriate to the event by human evaluators than those generated by existing methods.
2023-06-01
2023 IEEE International Conference on Robotics and Automation (ICRA) (published)
doi.org
arxiv.org
Generating Stable and Collision-Free Policies through Lyapunov Function Learning
Alexandre Coulombe
Hsiu-Chin Lin
The need for rapid and reliable robot deployment is on the rise. Imitation Learning (IL) has become popular for producing motion planning po… (see more)licies from a set of demonstrations. However, many methods in IL are not guaranteed to produce stable policies. The generated policy may not converge to the robot target, reducing reliability, and may collide with its environment, reducing the safety of the system. Stable Estimator of Dynamic Systems (SEDS) produces stable policies by constraining the Lyapunov stability criteria during learning, but the Lyapunov candidate function had to be manually selected. In this work, we propose a novel method for learning a Lyapunov function and a collision-free policy using a single neural network model. The method can be equipped with an obstacle avoidance module for convex object pairs to guarantee no collisions. We demonstrated our method is capable of finding policies in several simulation environments and transfer to a real-world scenario.
2023-06-01
2023 IEEE International Conference on Robotics and Automation (ICRA) (published)
doi.org
arxiv.org
Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans
Stefania Raimondo
Christopher Pal
Xiaotian Liu
David Vázquez
Hector. Palacios
2023-06-01
ArXiv (preprint)
doi.org
arxiv.org
Communication Load Balancing via Efficient Inverse Reinforcement Learning
Abhisek Konar
Di Wu
Yi Tian Xu
Seowoo Jang
Steve Liu
Gregory Dudek
Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for net… (see more)work systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function. In this work, we tackle the communication load balancing problem from an inverse reinforcement learning (IRL) approach. To the best of our knowledge, this is the first time IRL has been successfully applied in the field of communication load balancing. Specifically, first, we infer a reward function from a set of demonstrations, and then learn a reinforcement learning load balancing policy with the inferred reward function. Compared to classical RL-based solution, the proposed solution can be more general and more suitable for real-world scenarios. Experimental evaluations implemented on different simulated traffic scenarios have shown our method to be effective and better than other baselines by a considerable margin.
2023-05-31
ICC 2023 - IEEE International Conference on Communications (published)
doi.org
arxiv.org
Contrasted root trait responses between saplings of an arbuscular and an ectomycorrhizal tree species in open field compared to forest conditions
V. Parasquive
J. Brisson
X. Guilbeault‐Mayers
E. Laliberté
P. L. Chagnon
Plant nutrient acquisition strategies range along a spectrum from autonomous foraging to investment in cooperative foraging through mycorrhi… (see more)zal associations. However, in temperate ecosystems, many plant species encounter contrasted levels of symbiont availability in open fields versus closed forests. Little is known about how fungal partner availability may be associated with intraspecific variation in other root foraging traits in natural settings. Here, we addressed this issue by sampling saplings from two tree species: the arbuscular mycorrhizal (AM) Acer rubrum and the ectomycorrhizal (ECM) Quercus rubra from open fields (AM dominated) and adjacent forest plots (ECM dominated). For each species and environment, we measured morphological, architectural and symbiotic root traits. For the open field, Quercus had greater specific root length (SRL) while Acer had higher AM colonization and root diameter. In the closed forest, the opposite pattern was observed, namely Quercus had higher ECM colonization and Acer greater SRL. Both species showed evidence of a shift towards autonomous root foraging in the habitat with low expected symbiont abundance (open field for Quercus and forest for Acer ). Although the confounding effects of site abiotic properties could not be strictly controlled in this study, these results suggest that plants might adjust root foraging traits according to local habitat conditions. Synthesis : Our results shed new light on the intraspecific variation in plant position along the so‐called ‘collaboration gradient’, and suggest that mycorrhizal symbiont availability, along with other factors such as competition and site properties, may contribute to this variation.
2023-05-31
Journal of Ecology (published)
doi.org
Discussion of “Experimental Study of the Thixotropic Strength Recovery and Microstructural Evolution of Marine Clays”
Xianwei Zhang
Xinyu Liu
Gang Wang
2023-05-31
Journal of Geotechnical and Geoenvironmental Engineering (published)
doi.org
Fast Fine-Tuning Using Curriculum Domain Adaptation
Lulan Shen
Ibtihel Amara
Ruofeng Li
Brett Meyer
Warren Gross
James J. Clark
Current deep neural networks (DNNs) have achieved remarkable accuracy in various downstream tasks. However, their training and fine-tuning a… (see more)re challenging due to several factors, such as limited computational resources, extended training and fine-tuning times, and over-fitting due to small datasets. To address these challenges, we propose a three-stage fast fine-tuning method that efficiently trains DNNs for edge devices. Our method combines curriculum learning and domain adaptation techniques to accelerate training while achieving comparable performance. First, we develop a data curriculum approach, which ranks the dataset according to difficulty and split it into the source domain (containing easy data) and the target domain (containing difficult data). Second, we adapt the pretrained model from the source domain to the target domain using an unsupervised domain adaptation (UDA) method called Deep CORAL. Finally, we continue training the adapted model on the source domain with fewer epochs. Our method achieves high accuracy quickly on various modern neural network architectures and datasets such as CIFAR-10, CIFAR-100, and CINIC-10.
2023-05-31
Canadian Conference on Computer and Robot Vision (published)
doi.org
Geometry Regularized Autoencoders
Andres F. Duque Correa
Sacha Morin
Guy Wolf
Kevin R. Moon
A fundamental task in data exploration is to extract low dimensional representations that capture intrinsic geometry in data, especially for… (see more) faithfully visualizing data in two or three dimensions. Common approaches use kernel methods for manifold learning. However, these methods typically only provide an embedding of the input data and cannot extend naturally to new data points. Autoencoders have also become popular for representation learning. While they naturally compute feature extractors that are extendable to new data and invertible (i.e., reconstructing original features from latent representation), they often fail at representing the intrinsic data geometry compared to kernel-based manifold learning. We present a new method for integrating both approaches by incorporating a geometric regularization term in the bottleneck of the autoencoder. This regularization encourages the learned latent representation to follow the intrinsic data geometry, similar to manifold learning algorithms, while still enabling faithful extension to new data and preserving invertibility. We compare our approach to autoencoder models for manifold learning to provide qualitative and quantitative evidence of our advantages in preserving intrinsic structure, out of sample extension, and reconstruction. Our method is easily implemented for big-data applications, whereas other methods are limited in this regard.
2023-05-31
IEEE Transactions on Pattern Analysis and Machine Intelligence (published)
doi.org
Grow-push-prune: Aligning deep discriminants for effective structural network compression
Qing Tian
Tal Arbel
James J. Clark
2023-05-31
Computer Vision and Image Understanding (published)
doi.org
arxiv.org
HSV-2 triggers upregulation of MALAT1 in CD4+ T cells and promotes HIV latency reversal
Carl A. Pierce
Lip Nam Loh
Holly Steach
Natalia Cheshenko
Paula Preston-Hurlburt
Fengrui Zhang
Stephanie Stransky
Leah Kravets
Simone Sidoli
William Philbrick
Michel Nassar
Smita Krishnaswamy
Kevan C. Herold
Betsy C. Herold
Herpes simplex virus type 2 (HSV-2) coinfection is associated with increased HIV-1 viral loads and expanded tissue reservoirs, but the mecha… (see more)nisms are not well defined. HSV-2 recurrences result in an influx of activated CD4+ T cells to sites of viral replication and an increase in activated CD4+ T cells in peripheral blood. We hypothesized that HSV-2 induces changes in these cells that facilitate HIV-1 reactivation and replication and tested this hypothesis in human CD4+ T cells and 2D10 cells, a model of HIV-1 latency. HSV-2 promoted latency reversal in HSV-2–infected and bystander 2D10 cells. Bulk and single-cell RNA-Seq studies of activated primary human CD4+ T cells identified decreased expression of HIV-1 restriction factors and increased expression of transcripts including MALAT1 that could drive HIV replication in both the HSV-2–infected and bystander cells. Transfection of 2D10 cells with VP16, an HSV-2 protein that regulates transcription, significantly upregulated MALAT1 expression, decreased trimethylation of lysine 27 on histone H3 protein, and triggered HIV latency reversal. Knockout of MALAT1 from 2D10 cells abrogated the response to VP16 and reduced the response to HSV-2 infection. These results demonstrate that HSV-2 contributes to HIV-1 reactivation through diverse mechanisms, including upregulation of MALAT1 to release epigenetic silencing.
2023-05-31
The Journal of Clinical Investigation (published)
doi.org