Publications

A Halfspace-Mass Depth-Based Method for Adversarial Attack Detection
Marine Picot
Federica Granese
Guillaume Staerman
Marco Romanelli
Francisco Messina
Pablo Piantanida
Pierre Colombo
2023-03-27
TMLR (accepté)
openreview.net
openreview.net
Green Federated Learning
Ashkan Yousefpour
Sheng Guo
Ashish V. Shenoy
Sayan Ghosh
Pierre Stock
Kiwan Maeng
Schalk-Willem Kruger
Michael G. Rabbat
Carole-Jean Wu
Ilya Mironov
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets. As a consequenc… (voir plus)e, the amount of compute used in training state-of-the-art models is exponentially increasing (doubling every 10 months between 2015 and 2022), resulting in a large carbon footprint. Federated Learning (FL) - a collaborative machine learning technique for training a centralized model using data of decentralized entities - can also be resource-intensive and have a significant carbon footprint, particularly when deployed at scale. Unlike centralized AI that can reliably tap into renewables at strategically placed data centers, cross-device FL may leverage as many as hundreds of millions of globally distributed end-user devices with diverse energy sources. Green AI is a novel and important research area where carbon footprint is regarded as an evaluation criterion for AI, alongside accuracy, convergence speed, and other metrics. In this paper, we propose the concept of Green FL, which involves optimizing FL parameters and making design choices to minimize carbon emissions consistent with competitive performance and training time. The contributions of this work are two-fold. First, we adopt a data-driven approach to quantify the carbon emissions of FL by directly measuring real-world at-scale FL tasks running on millions of phones. Second, we present challenges, guidelines, and lessons learned from studying the trade-off between energy efficiency, performance, and time-to-train in a production FL system. Our findings offer valuable insights into how FL can reduce its carbon footprint, and they provide a foundation for future research in the area of Green AI.
2023-03-25
ArXiv (prépublication)
doi.org
arxiv.org
Evolutionary history explains foliar spectral differences between arbuscular and ectomycorrhizal plant species
Johanna R. Jantzen
Étienne Laliberté
Alexis Carteron
Rosalie Beauchamp‐Rioux
Florence Blanchard
Anna L. Crofts
Alizée Girard
Paul W. Hacker
Juliana Pardo
Anna K. Schweiger
Sabrina Demers‐Thibeault
Nicholas C. Coops
Margaret Kalácska
Mark Vellend
Anne Bruneau
Leaf spectra are integrated foliar phenotypes that capture a range of traits and can provide insight into ecological processes. Leaf traits,… (voir plus) and therefore leaf spectra, may reflect belowground processes such as mycorrhizal associations. However, evidence for the relationship between leaf traits and mycorrhizal association is mixed, and few studies account for shared evolutionary history. We conduct partial least squares discriminant analysis to assess the ability of spectra to predict mycorrhizal type. We model the evolution of leaf spectra for 92 vascular plant species and use phylogenetic comparative methods to assess differences in spectral properties between arbuscular mycorrhizal and ectomycorrhizal plant species. Partial least squares discriminant analysis classified spectra by mycorrhizal type with 90% (arbuscular) and 85% (ectomycorrhizal) accuracy. Univariate models of principal components identified multiple spectral optima corresponding with mycorrhizal type due to the close relationship between mycorrhizal type and phylogeny. Importantly, we found that spectra of arbuscular mycorrhizal and ectomycorrhizal species do not statistically differ from each other after accounting for phylogeny. While mycorrhizal type can be predicted from spectra, enabling the use of spectra to identify belowground traits using remote sensing, this is due to evolutionary history and not because of fundamental differences in leaf spectra due to mycorrhizal type.
2023-03-23
New Phytologist (publié)
doi.org
Catalyzing next-generation Artificial Intelligence through NeuroAI
Anthony Zador
Blake Aaron Richards
Bence Ölveczky
Sean Escola
Yoshua Bengio
Kwabena Boahen
Matthew Botvinick
Dmitri Chklovskii
Anne Churchland
Claudia Clopath
James DiCarlo
Surya Ganguli
Jeff Hawkins
Konrad Paul Kording
Alexei Koulakov
Yann Lecun
Timothy P Lillicrap
Adam Marblestone
Bruno Olshausen
Alexandre Pouget … (voir 7 de plus)
Cristina Savin
Terrence Sejnowski
Eero Simoncelli
Sara Solla
David Sussillo
Andreas S. Tolias
Doris Tsao
2023-03-21
Nature Communications (publié)
doi.org
arxiv.org
A Novel Model for Novelty: Modeling the Emergence of Innovation from Cumulative Culture
Natalie Kastel
Guillaume Dumas
2023-03-21
Active Inference (publié)
doi.org
Posthoc Interpretation via Quantization
Yusuf Cem Sübakan
Francesco Paissan
Mirco Ravanaelli
In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained… (voir plus) classifiers. Our method utilizes vector quantization to transform the representations of a classifier into a discrete, class-specific latent space. The class-specific codebooks act as a bottleneck that forces the interpreter to focus on the parts of the input data deemed relevant by the classifier for making a prediction. Our model formulation also enables learning concepts by incorporating the supervision of pretrained annotation models such as state-of-the-art image segmentation models. We evaluated our method through quantitative and qualitative studies involving black-and-white images, color images, and audio. As a result of these studies we found that PIQ generates interpretations that are more easily understood by participants to our user studies when compared to several other interpretation methods in the literature.
2023-03-21
arXiv (prépublication)
doi.org
arxiv.org
Electromagnetic interference shielding in lightweight carbon xerogels
Biporjoy Sarkar
Floriane Miquet-Westphal
Sanyasi Bobbara
Ben George
Giovanni Beltrame
David Dousset
Ke Wu
Fabio Cicoira
With the increasing use of high-frequency electronic and wireless devices, electromagnetic interference (EMI) has become a growing concern d… (voir plus)ue to its potential impact on both electronic devices and human health. In this study, we demonstrated the performance of lightweight, electrically conducting 3D resorcinol-formaldehyde carbon xerogels, of 2.4 mm thickness, as an EMI shieldin the frequency range of 10–15 GHz (X-Ku band). The brittle carbon xerogels revealed complex porous structures with irregularly shaped pores that were randomly distributed. Electrochemical characterization revealed that the material behaved as an electrical double-layer capacitor. The carbon xerogels displayed reflection-dominated (∼ 84%) shielding behavior, with a total EMI shielding effectiveness (SE) value of ∼ 61 dB. The absorption process also contributed (∼ 16%) to the total SE. This behavior is attributed to the carbon xerogels' complex porous network, which effectively suppresses EM waves.
2023-03-20
Materials Research Express (publié)
doi.org
Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT
Vincent Andrearczyk
Valentin Oreiller
Moamen A. Abobakr
Azadeh Akhavanallaf
Panagiotis Balermpas
Sarah Boughdad
Leo Capriotti
Joel Castelli
Catherine Cheze Le Rest
Pierre Decazes
Ricardo Correia
D. El-Habashy
Hesham M. Elhalawani
C. Fuller
Mario Jreige
Yomna Khamis
Agustina La Greca Saint-Esteven
Aliae Ar Hussein Mohamed
M. Naser
John O. Prior … (voir 11 de plus)
Su Ruan
Stephanie Tanadini-Lang
Olena Tankyevych
Yazdan Salimi
Martin Vallières
Pierre Véra
Dimitris Visvikis
K. Wahid
Habib Zaidi
Mathieu Hatt
Adrien Depeursinge
2023-03-17
Lecture Notes in Computer Science (publié)
doi.org
Behavioral Cloning for Crystal Design
Prashant Govindarajan
Santiago Miret
Jarrid Rector-Brooks
Mariano Phielipp
Janarthanan Rajendran
A. Chandar
Solid-state materials, which are made up of periodic 3D crystal structures, are particularly useful for a variety of real-world applications… (voir plus) such as batteries, fuel cells and catalytic materials. Designing solid-state materials, especially in a robust and automated fashion, remains an ongoing challenge. To further the automated design of crystalline materials, we propose a method to learn to design valid crystal structures given a crystal skeleton. By incorporating Euclidean equivariance into a policy network, we portray the problem of designing new crystals as a sequential prediction task suited for imitation learning. At each step, given an incomplete graph of a crystal skeleton, an agent assigns an element to a specific node. We adopt a behavioral cloning strategy to train the policy network on data consisting of curated trajectories generated from known crystals.
2023-03-16
ICLR.cc/2023/Workshop/ML4Materials (poster)
openreview.net
openreview.net
Spatial Hard Attention Modeling via Deep Reinforcement Learning for Skeleton-Based Human Activity Recognition
Bahareh Nikpour
Narges Armanfard
Deep learning-based algorithms have been very successful in skeleton-based human activity recognition. Skeleton data contains 2-D or 3-D coo… (voir plus)rdinates of human body joints. The main focus of most of the existing skeleton-based activity recognition methods is on designing new deep architectures to learn discriminative features, where all body joints are considered equally important in recognition. However, the importance of joints varies as an activity proceeds within a video and across different activities. In this work, we hypothesize that selecting relevant joints, prior to recognition, can enhance performance of the existing deep learning-based recognition models. We propose a spatial hard attention finding method that aims to remove the uninformative and/or misleading joints at each frame. We formulate the joint selection problem as a Markov decision process and employ deep reinforcement learning to train the proposed spatial-attention-aware agent. No extra labels are needed for the agent’s training. The agent takes a sequence of features extracted from skeleton video as input and outputs a sequence of probabilities for joints. The proposed method can be considered as a general framework that can be integrated with the existing skeleton-based activity recognition methods for performance improvement purposes. We obtain very competitive activity recognition results on three commonly used human activity recognition datasets.
2023-03-16
IEEE Transactions on Systems, Man, and Cybernetics: Systems (inconnu)
doi.org
Transitions between cognitive topographies: contributions of network structure, neuromodulation, and disease
Andrea I. Luppi
S. Parker Singleton
Justine Y. Hansen
Danilo Bzdok
Amy Kuceyeski
Richard F. Betzel
Bratislav Misic
Patterns of neural activity underlie human cognition. Transitions between these patterns are orchestrated by the brain’s network architect… (voir plus)ure. What are the mechanisms linking network structure to cognitively relevant activation patterns? Here we implement principles of network control to investigate how the architecture of the human connectome shapes transitions between 123 experimentally defined cognitive activation maps (cognitive topographies) from the NeuroSynth meta-analytic engine. We also systematically incorporate neurotransmitter receptor density maps (18 receptors and transporters) and disease-related cortical abnormality maps (11 neurodegenerative, psychiatric and neurodevelopmental diseases; N = 17 000 patients, N = 22 000 controls). Integrating large-scale multimodal neuroimaging data from functional MRI, diffusion tractography, cortical morphometry, and positron emission tomography, we simulate how anatomically-guided transitions between cognitive states can be reshaped by pharmacological or pathological perturbation. Our results provide a comprehensive look-up table charting how brain network organisation and chemoarchitecture interact to manifest different cognitive topographies. This computational framework establishes a principled foundation for systematically identifying novel ways to promote selective transitions between desired cognitive topographies.
2023-03-16
bioRxiv (prépublication)
doi.org
Instance-Conditioned GAN Data Augmentation for Representation Learning
Pietro Astolfi
Arantxa Casanova
Jakob Verbeek
P Vincent
Adriana Romero
Michal Drozdzal
2023-03-15
ArXiv (prépublication)
doi.org
arxiv.org