Ensemble Distillation for Robust Model Fusion in Federated Learning

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning (ML) applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks (NNs) to learn from high-dimensional data ...

Reduced-order models (ROMs) are widely used in scientific computing to tackle high-dimensional systems. However, traditional ROM methods may only partially capture the intrinsic geometric characteristics of the data. These characteristics encompass the und ...

To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic segmentation scenario, suc ...

Approximate multipliers (AppMults) are widely employed in deep neural network (DNN) accelerators to reduce the area, delay, and power consumption. However, the inaccuracies of AppMults degrade DNN accuracy, necessitating a retraining process to recover acc ...

Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with varying orientat ...

Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale description of molecules and materials. Among the many different approaches that h ...

Koopmans spectral functionals are a powerful extension of Kohn-Sham density-functional theory (DFT) that enables the prediction of spectral properties with state-of-the-art accuracy. The success of these functionals relies on capturing the effects of elect ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Combined high-fusion performance and long-pulse operation is one of the key integration challenges for fusion energy development in magnetic devices. Addressing these challenges requires an integrated vision of physics and engineering aspects with the purp ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

The impact of plasma shaping on the properties of high density H-mode scrape-off layer (SOL) profiles and transport at the outer midplane has been investigated on Tokamaka configuration variable. The experimental dataset has been acquired by evolving the u ...

Nuclear fusion presents a promising clean energy source to mitigate future energy crises, with magnetic confinement fusion well-positioned to provide a baseload scenario to power future reactors. The unmitigated power exhaust of such reactors threatens its ...

Operators from various industries have been pushing the adoption of wireless sensing nodes for industrial monitoring, and such efforts have produced sizeable condition monitoring datasets that can be used to build diagnosis algorithms capable of warning ma ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

MAST-U is equipped with on-axis and off-axis neutral beam injectors (NBI), and these external sources of super-Alfv & eacute;nic deuterium fast-ions provide opportunities for studying a wide range of phenomena relevant to the physics of alpha-particles in ...

In order to cope with the decarbonization challenge faced by many countries, fusion is one of the few alternatives to fossil fuels for the production of electricity. Two devices invented in the middle of the previous century have emerged as the most promis ...

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

Ensemble Distillation for Robust Model Fusion in Federated Learning

Chat with Graph Search

High-dimensional learning of narrow neural networks

OPTIMAL TRANSPORT-INSPIRED DEEP LEARNING FRAMEWORK FOR SLOW-DECAYING KOLMOGOROV \bfitn-WIDTH PROBLEMS: EXPLOITING SINKHORN LOSS AND WASSERSTEIN KERNEL

Exploiting XAI Maps to Improve MS Lesion Segmentation and Detection in MRI

Gradient Approximation of Approximate Multipliers for High-Accuracy Deep Neural Network Retraining

ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations

Wigner kernels: Body-ordered equivariant machine learning without a basis

Predicting electronic screening for fast Koopmans spectral functional calculations

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Long plasma duration operation analyses with an international multi-machine (tokamaks and stellarators) database

Topics in statistical physics of high-dimensional machine learning

Robust machine learning for neuroscientific inference

On the Generalization of Stochastic Gradient Descent with Momentum

Meta-learning to address diverse Earth observation problems across resolutions

The effect of plasma shaping on high density H-mode SOL profiles and fluctuations in TCV

Experimental study and interpretative modelling of the Power Exhaust in Configurations with Multiple X-Points in TCV

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

Random matrix methods for high-dimensional machine learning models

Overview of fast particle experiments in the first MAST Upgrade experimental campaigns

Global fluid simulations of plasma turbulence in stellarators

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life