Publications

BIAS: Transparent reporting of biomedical image analysis challenges
Lena Maier-Hein
Annika Reinke
Michal Kozubek
Anne L. Martel
Tal Arbel
Matthias Eisenmann
Allan Hanbury
Pierre Jannin
Henning Müller
Sinan Onogur
Julio Saez-Rodriguez
Bram van Ginneken
Annette Kopp-Schneider
Bennett Landman
2020-08-20
Medical Image Analysis (publié)
doi.org
arxiv.org
Precision, Equity, and Public Health and Epidemiology Informatics – A Scoping Review
David L Buckeridge
2020-08-20
Yearbook of Medical Informatics (publié)
doi.org
Laplacian Change Point Detection for Dynamic Graphs
Shenyang Huang
Yasmeen Hitti
Guillaume Rabusseau
Reihaneh Rabbany
2020-08-19
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (publié)
doi.org
arxiv.org
Fast reinforcement learning with generalized policy updates
Andre Barreto
Shaobo Hou
Diana Borsa
David Silver
Doina Precup
The combination of reinforcement learning with deep learning is a promising approach to tackle important sequential decision-making problems… (voir plus) that are currently intractable. One obstacle to overcome is the amount of data needed by learning systems of this type. In this article, we propose to address this issue through a divide-and-conquer approach. We argue that complex decision problems can be naturally decomposed into multiple tasks that unfold in sequence or in parallel. By associating each task with a reward function, this problem decomposition can be seamlessly accommodated within the standard reinforcement-learning formalism. The specific way we do so is through a generalization of two fundamental operations in reinforcement learning: policy improvement and policy evaluation. The generalized version of these operations allow one to leverage the solution of some tasks to speed up the solution of others. If the reward function of a task can be well approximated as a linear combination of the reward functions of tasks previously solved, we can reduce a reinforcement-learning problem to a simpler linear regression. When this is not the case, the agent can still exploit the task solutions by using them to interact with and learn about the environment. Both strategies considerably reduce the amount of data needed to solve a reinforcement-learning problem.
2020-08-16
Proceedings of the National Academy of Sciences of the United States of America (publié)
doi.org
Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds
Michael Perlmutter
Feng Gao
Guy Wolf
Matthew Hirn
The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural netw… (voir plus)orks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional neural networks to manifold and graph-structured domains, we define a geometric scattering transform on manifolds. Similar to the Euclidean scattering transform, the geometric scattering transform is based on a cascade of wavelet filters and pointwise nonlinearities. It is invariant to local isometries and stable to certain types of diffeomorphisms. Empirical results demonstrate its utility on several geometric learning tasks. Our results generalize the deformation stability and local translation invariance of Euclidean scattering, and demonstrate the importance of linking the used filter structures to the underlying geometry of the data.
2020-08-15
Mathematical and Scientific Machine Learning Conference (publié)
doi.org
proceedings.mlr.press
Mastering Rate based Curriculum Learning
Lucas Willems
Salem Lahlou
Yoshua Bengio
2020-08-13
arXiv (prépublication)
doi.org
arxiv.org
Quantitative MRI of the spinal cord: Reproducibility and normative values across 40 sites
Eva Alonso‐Ortiz
Charley Gros
Alexandru Foias
Mihael Abramovic
Christoph Arneitz
Nicole Atcheson
Laura Barlow
Robert Barry
Markus Barth
Marco Battiston
Christian Büchel
Matthew D. Budde
Virginie Callot
Benjamin De Leener
Maxime Descoteaux
Paulo Loureiro de Sousa
Marek Dostál
Julien Doyon
Adam Dvorak
Falk Eippert … (voir 60 de plus)
Karla R. Epperson
Jürgen Finsterbusch
Issei Fukunaga
Claudia A. M. Gandini Wheeler‐Kingshott
Giancarlo Germani
Guillaume Gilbert
Francesco Grussu
Akifumi Hagiwara
Pierre‐Gilles Henry
Thomas Horak
Masaaki Hori
James M. Joers
Kouhei Kamiya
Haleh Karbasforoushan
Ali Khatibi
Joo-Won Kim
Nawal Kinany
Hagen H. Kitzler
Shannon Kolind
Joe Yazhuo Kong
Shannon Kolind
Paul Kuntke
Nyoman D. Kurniawan
Sławomir Kuśmia
René Labounek
Maria Marcella Laganà
Corree Laule
Christine Law
Christophe Lenglet
Tobias Leutritz
Yaou Liu
Sara Llufriú
Sean Mackey
Eloy Jiménez Martínez
Igor Nestrašil
Nico Papinutto
Daniel S. Papp
Deborah Pareto
Todd B. Parrish
Anna Pichiecchio
À. Rovira Cañellas
Marc J. Ruitenberg
Rebecca S. Samson
G. Savini
Maryam Seif
Alan C. Seifert
Alex K. Smith
Zachary A. Smith
Elisabeth Solana
Yuichi Suzuki
George Tackley
Alexandra Tinnermann
Jan Valosek
Marios Yiannakas
Kenneth A. Weber
Nikolaus Weiskopf
Richard G. Wise
Patrik O. Wyss
Junqian Xu
Julien Cohen‐Adad
2020-08-13
PolyPublie (École Polytechnique de Montréal) (accepté)
www.semanticscholar.org
Adaptive Learning of Tensor Network Structures
Meraj Hashemizadeh
Michelle Liu
Jacob Miller
Guillaume Rabusseau
Tensor Networks (TN) offer a powerful framework to efficiently represent very high-dimensional objects. TN have recently shown their potenti… (voir plus)al for machine learning applications and offer a unifying view of common tensor decomposition models such as Tucker, tensor train (TT) and tensor ring (TR). However, identifying the best tensor network structure from data for a given task is challenging. In this work, we leverage the TN formalism to develop a generic and efficient adaptive algorithm to jointly learn the structure and the parameters of a TN from data. Our method is based on a simple greedy approach starting from a rank one tensor and successively identifying the most promising tensor network edges for small rank increments. Our algorithm can adaptively identify TN structures with small number of parameters that effectively optimize any differentiable objective function. Experiments on tensor decomposition, tensor completion and model compression tasks demonstrate the effectiveness of the proposed algorithm. In particular, our method outperforms the state-of-the-art evolutionary topology search [Li and Sun, 2020] for tensor decomposition of images (while being orders of magnitude faster) and finds efficient tensor network structures to compress neural networks outperforming popular TT based approaches [Novikov et al., 2015].
2020-08-11
ArXiv (prépublication)
openreview.net
openreview.net
Prediction, Not Association, Paves the Road to Precision Medicine
Danilo Bzdok
Gael Varoquaux
Ewout W. Steyerberg
2020-08-11
JAMA Psychiatry (publié)
doi.org
Robust motion in-betweening
Félix Harvey
Mike Yurick
D. Nowrouzezahrai
Christopher Pal
In this work we present a novel, robust transition generation technique that can serve as a new tool for 3D animators, based on adversarial … (voir plus)recurrent neural networks. The system synthesises high-quality motions that use temporally-sparse keyframes as animation constraints. This is reminiscent of the job of in-betweening in traditional animation pipelines, in which an animator draws motion frames between provided keyframes. We first show that a state-of-the-art motion prediction model cannot be easily converted into a robust transition generator when only adding conditioning information about future keyframes. To solve this problem, we then propose two novel additive embedding modifiers that are applied at each timestep to latent representations encoded inside the network's architecture. One modifier is a time-to-arrival embedding that allows variations of the transition length with a single model. The other is a scheduled target noise vector that allows the system to be robust to target distortions and to sample different transitions given fixed keyframes. To qualitatively evaluate our method, we present a custom MotionBuilder plugin that uses our trained model to perform in-betweening in production scenarios. To quantitatively evaluate performance on transitions and generalizations to longer time horizons, we present well-defined in-betweening benchmarks on a subset of the widely used Human3.6M dataset and on LaFAN1, a novel high quality motion capture dataset that is more appropriate for transition generation. We are releasing this new dataset along with this work, with accompanying code for reproducing our baseline results.
2020-08-11
ACM Transactions on Graphics (publié)
doi.org
arxiv.org
Meta-matching: a simple framework to translate phenotypic predictive models from big to small data
Tong He
Lijun An
Jiashi Feng
Danilo Bzdok
Avram J Holmes
Simon B. Eickhoff
B.T. Thomas Yeo
There is significant interest in using brain imaging data to predict non-brain-imaging phenotypes in individual participants. However, most … (voir plus)prediction studies are underpowered, relying on less than a few hundred participants, leading to low reliability and inflated prediction performance. Yet, small sample sizes are unavoidable when studying clinical populations or addressing focused neuroscience questions. Here, we propose a simple framework – “meta-matching” – to translate predictive models from large-scale datasets to new unseen non-brain-imaging phenotypes in boutique studies. The key observation is that many large-scale datasets collect a wide range inter-correlated phenotypic measures. Therefore, a unique phenotype from a boutique study likely correlates with (but is not the same as) some phenotypes in some large-scale datasets. Meta-matching exploits these correlations to boost prediction in the boutique study. We applied meta-matching to the problem of predicting non-brain-imaging phenotypes using resting-state functional connectivity (RSFC). Using the UK Biobank (N = 36,848), we demonstrated that meta-matching can boost the prediction of new phenotypes in small independent datasets by 100% to 400% in many scenarios. When considering relative prediction performance, meta-matching significantly improved phenotypic prediction even in samples with 10 participants. When considering absolute prediction performance, meta-matching significantly improved phenotypic prediction when there were least 50 participants. With a growing number of large-scale population-level datasets collecting an increasing number of phenotypic measures, our results represent a lower bound on the potential of meta-matching to elevate small-scale boutique studies.
2020-08-10
bioRxiv (prépublication)
doi.org
Hidden population modes in social brain morphology: Its parts are more than its sum
Hannah Kiesow
R. Nathan Spreng
Avram J. Holmes
M. Mallar Chakravarty
Andre F. Marquand
B.T. Thomas Yeo
Danilo Bzdok
The complexity of social interactions is a defining property of the human species. Many social neuroscience experiments have sought to map … (voir plus)perspective taking’, ‘empathy’, and other canonical psychological constructs to distinguishable brain circuits. This predominant research paradigm was seldom complemented by bottom-up studies of the unknown sources of variation that add up to measures of social brain structure; perhaps due to a lack of large population datasets. We aimed at a systematic de-construction of social brain morphology into its elementary building blocks in the UK Biobank cohort (n=~10,000). Coherent patterns of structural co-variation were explored within a recent atlas of social brain locations, enabled through translating autoencoder algorithms from deep learning. The artificial neural networks learned rich subnetwork representations that became apparent from social brain variation at population scale. The learned subnetworks carried essential information about the co-dependence configurations between social brain regions, with the nucleus accumbens, medial prefrontal cortex, and temporoparietal junction embedded at the core. Some of the uncovered subnetworks contributed to predicting examined social traits in general, while other subnetworks helped predict specific facets of social functioning, such as feelings of loneliness. Our population-level evidence indicates that hidden subsystems of the social brain underpin interindividual variation in dissociable aspects of social lifestyle.
2020-08-06
bioRxiv (prépublication)
doi.org