Publications

Isometric Energies for Recovering Injectivity in Constrained Mapping
Xingyi Du
Danny M. Kaufman
Qingnan Zhou
Shahar Kovalsky
Yajie Yan
Noam Aigerman
Tao Ju
2022-11-29
ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (published)
doi.org
Continual Learning with Foundation Models: An Empirical Study of Latent Replay
Oleksiy Ostapenko
Timothee LESORT
Pau Rodriguez
Md Rifat Arefin
Arthur Douillard
Irina Rish
Laurent Charlin
Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of… (see more) downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios. Our goal is twofold. First, we want to understand the compute-accuracy trade-off between CL in the raw-data space and in the latent space of pre-trained encoders. Second, we investigate how the characteristics of the encoder, the pre-training algorithm and data, as well as of the resulting latent space affect CL performance. For this, we compare the efficacy of various pre-trained models in large-scale benchmarking scenarios with a vanilla replay setting applied in the latent and in the raw-data space. Notably, this study shows how transfer, forgetting, task similarity and learning are dependent on the input data characteristics and not necessarily on the CL algorithms. First, we show that under some circumstances reasonable CL performance can readily be achieved with a non-parametric classifier at negligible compute. We then show how models pre-trained on broader data result in better performance for various replay sizes. We explain this with representational similarity and transfer properties of these representations. Finally, we show the effectiveness of self-supervised pre-training for downstream domains that are out-of-distribution as compared to the pre-training domain. We point out and validate several research directions that can further increase the efficacy of latent CL including representation ensembling. The diverse set of datasets used in this study can serve as a compute-efficient playground for further CL research. We will publish the code.
2022-11-28
Proceedings of The 1st Conference on Lifelong Learning Agents (published)
proceedings.mlr.press
arxiv.org
Shimming toolbox: An open‐source software toolbox for <scp>B0</scp> and <scp>B1</scp> shimming in MRI
Alexandre D'Astous
Gaspard Cereza
Daniel Papp
Kyle M. Gilbert
Jason P. Stockmann
Eva Alonso‐Ortiz
Julien Cohen-Adad
2022-11-28
Magnetic Resonance in Medicine (published)
doi.org
Applied artificial intelligence in healthcare: Listening to the winds of change in a post-COVID-19 world
Arash Shaban-Nejad
Martin Michalowski
Simone Bianco
John S. Brownstein
David Buckeridge
Robert L Davis
2022-11-25
Experimental Biology and Medicine (published)
doi.org
Beyond Mahalanobis-Based Scores for Textual OOD Detection
Pierre Colombo
Eduardo Dadalto Câmara Gomes
Guillaume Staerman
Nathan Noiry
Pablo Piantanida
2022-11-24
ArXiv (preprint)
doi.org
arxiv.org
Towards Adaptive Cybersecurity for Green IoT
Talal Halabi
Martine Bellaiche
Benjamin Fung
The Internet of Things (IoT) paradigm has led to an explosion in the number of IoT devices and an exponential rise in carbon footprint incur… (see more)red by overburdened IoT networks and pervasive cloud/edge communications. Hence, there is a growing interest in industry and academia to enable the efficient use of computing infrastructures by optimizing the management of data center and IoT resources (hardware, software, network, and data) and reducing operational costs to slash greenhouse gas emissions and create healthy environments. Cybersecurity has also been considered in such efforts as a contributor to these environmental issues. Nonetheless, most green security approaches focus on designing low-overhead encryption schemes and do not emphasize energy-efficient security from architectural and deployment viewpoints. This paper sheds light on the emerging paradigm of adaptive cybersecurity as one of the research directions to support sustainable computing in green IoT. It presents three potential research directions and their associated methods for designing and deploying adaptive security in green computing and resource-constrained IoT environments to save on energy consumption. Such efforts will transform the development of data-driven IoT security solutions to be greener and more environment-friendly.
2022-11-24
2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS) (published)
doi.org
Age differences in functional brain networks associated with loneliness and empathy
Laetitia Mwilambwe-Tshilobo
Roni Setton
Danilo Bzdok
Gary R. Turner
R. Nathan Spreng
Abstract Loneliness is associated with differences in resting-state functional connectivity (RSFC) within and between large-scale networks i… (see more)n early- and middle-aged adult cohorts. However, age-related changes in associations between sociality and brain function into late adulthood are not well understood. Here, we examined age differences in the association between two dimensions of sociality—loneliness and empathic responding—and RSFC of the cerebral cortex. Self-report measures of loneliness and empathy were inversely related across the entire sample of younger (mean age = 22.6y, n = 128) and older (mean age = 69.0y, n = 92) adults. Using multivariate analyses of multi-echo fMRI RSFC, we identified distinct functional connectivity patterns for individual and age group differences associated with loneliness and empathic responding. Loneliness in young and empathy in both age groups was related to greater visual network integration with association networks (e.g., default, fronto-parietal control). In contrast, loneliness was positively related to within- and between-network integration of association networks for older adults. These results extend our previous findings in early- and middle-aged cohorts, demonstrating that brain systems associated with loneliness, as well as empathy, differ in older age. Further, the findings suggest that these two aspects of social experience engage different neurocognitive processes across human life-span development.
2022-11-23
Network Neuroscience (published)
doi.org
Momentum Extragradient is Optimal for Games with Cross-Shaped Spectrum
Junhyung Lyle Kim
Gauthier Gidel
Anastasios Kyrillidis
Fabian Pedregosa
Google Research
© J.l. Kim
The extragradient method has recently gained a lot of attention, due to its convergence behavior on smooth games. In games, the eigenvalues … (see more)of the Jacobian of the vector field are distributed on the complex plane, exhibiting more convoluted dynamics compared to minimization. In this work, we take a polynomial-based analysis of the extragradient with momentum for optimizing games with \emph{cross-shaped} spectrum on the complex plane. We show two results: first, the extragradient with momentum exhibits three different modes of convergence based on the hyperparameter setup: when the eigenvalues are distributed
2022-11-23
NeurIPS.cc/2022/Workshop/OPT (poster)
openreview.net
openreview.net
GraphCG: Unsupervised Discovery of Steerable Factors in Graphs
Shengchao Liu
Chengpeng Wang
Weili Nie
Hanchen Wang
Jiarui Lu
Bolei Zhou
Jian Tang
Deep generative models have been extensively explored recently, especially for the graph data such as molecular graphs and point clouds. Yet… (see more), much less investigation has been carried out on understanding the learned latent space of deep graph generative models. Such understandings can open up a unified perspective and provide guidelines for essential tasks like controllable generation. In this paper, we first examine the representation space of the recent deep generative model trained for graph data, observing that the learned representation space is not perfectly disentangled. Based on this observation, we then propose an unsupervised method called GraphCG, which is model-agnostic and task-agnostic for discovering steerable factors in graph data. Specifically, GraphCG learns the semantic-rich directions via maximizing the corresponding mutual information, where the edited graph along the same direction will possess certain steerable factors. We conduct experiments on two types of graph data, molecular graphs and point clouds. Both the quantitative and qualitative results show the effectiveness of GraphCG for discovering steerable factors. The code will be public in the near future.
2022-11-22
NeurIPS.cc/2022/Workshop/GLFrontiers (published)
openreview.net
openreview.net
SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows
Vikram Voleti
Boris Oreshkin
Florent Bocquelet
Félix Harvey
Louis-Simon Ménard
Chris Pal
2022-11-22
SIGGRAPH Asia 2022 Technical Communications (published)
doi.org
arxiv.org
Assessing the potential for virtualizable care in the pediatric emergency department.
Esli Osmanlliu
Brett Burstein
Robyn Tamblyn
David Buckeridge
INTRODUCTION There is increasing interest for patient-to-provider telemedicine in pediatric acute care. The suitability of telemedicine (vir… (see more)tualizability) for visits in this setting has not been formally assessed. We estimated the proportion of in-person pediatric emergency department (PED) visits that were potentially virtualizable, and identified factors associated with virtualizable care. METHODS This was a retrospective analysis of in-person visits at the PED of a Canadian tertiary pediatric hospital (02/2018-12/2019). Three definitions of virtualizable care were developed: (1) a definition based on "resource use" classifying visits as virtualizable if they resulted in a home discharge, no diagnostic testing, and no return visit within 72 h; (2) a "diagnostic definition" based on primary ED diagnosis; and (3) a stringent "combined definition" by which visits were classified as virtualizable if they met both the resource use and diagnostic definitions. Multivariable logistic regression was used to identify factors associated with telemedicine suitability. RESULTS There were 130,535 eligible visits from 80,727 individual patients during the study period. Using the most stringent combined definition of telemedicine suitability, 37.9% (95% confidence interval (CI) 37.6%-38.2%) of in-person visits were virtualizable. Overnight visits (adjusted odds ratio (aOR) 1.16-1.37), non-Canadian citizenship (aOR 1.10-1.18), ethnocultural vulnerability (aOR 1.14-1.22), and a consultation for head trauma (aOR 3.50-4.60) were associated with higher telemedicine suitability across definitions. DISCUSSION There is a high potential for patient-to-provider telemedicine in the PED setting. Local patient and visit-level characteristics must be considered in the design of safe and inclusive telemedicine models for pediatric acute care.
2022-11-20
Journal of Telemedicine and Telecare (published)
doi.org
Learning from uncertain concepts via test time interventions
Ivaxi Sheth
Aamer Abdul Rahman
Laya Rafiee Sevyeri
Mohammad Havaei
Samira Ebrahimi Kahou
With neural networks applied to safety-critical applications, it has become increasingly important to understand the defining features of de… (see more)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.
2022-11-20
NeurIPS.cc/2022/Workshop/TSRML (accepted)
openreview.net
openreview.net