Publications

Green Federated Learning

Ashkan Yousefpour

Sheng Guo

Ashish V. Shenoy

Sayan Ghosh

Pierre Stock

Kiwan Maeng

Schalk-Willem Kruger

Michael 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… (see more)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.

2023-03-26

ArXiv (preprint)

doi.org

arxiv.org

A Novel Model for Novelty: Modeling the Emergence of Innovation from Cumulative Culture

Natalie Kastel

Guillaume Dumas

2023-03-22

Active Inference (published)

doi.org

Posthoc Interpretation via Quantization

Cem (Yusuf) Subakan

Francesco Paissan

Mirco Ravanelli

In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained… (see more) 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.

2023-03-22

ArXiv (preprint)

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… (see more)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.

2023-03-21

Materials Research Express (published)

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

A. Mohamed

M. Naser

John O. Prior … (see 11 more)

Su Ruan

Stephanie Tanadini-Lang

Olena Tankyevych

Yazdan Salimi

Martin Vallières

Pierre Véra

Dimitris Visvikis

K. Wahid

Habib Zaidi

Mathieu Hatt

Adrien Depeursinge

2023-03-18

Lecture Notes in Computer Science (published)

doi.org

Behavioral Cloning for Crystal Design

Prashant Govindarajan

Santiago Miret

Jarrid Rector-Brooks

Mariano Phielipp

Janarthanan Rajendran

Sarath Chandar

Solid-state materials, which are made up of periodic 3D crystal structures, are particularly useful for a variety of real-world applications… (see more) 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.

2023-03-17

ICLR.cc/2023/Workshop/ML4Materials (poster)

openreview.net