Data-Aware Privacy-Preserving Machine 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.

Deep heteroscedastic regression involves jointly optimizing the mean and covariance of the predicted distribution using the negative log-likelihood. However, recent works show that this may result in sub-optimal convergence due to the challenges associated ...

Obesity represents a significant public health concern and is linked to various comorbidities and cognitive impairments. Previous research indicates that elevated body mass index (BMI) is associated with structural changes in white matter (WM). However, a ...

The spatial distribution of dwarf galaxies around their host galaxies is a critical test for the standard model of cosmology because it probes the dynamics of dark matter halos and is independent of the internal baryonic processes of galaxies. Comoving pla ...

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 ...

Graph Neural Networks (GNNs) have become a popular tool for learning on graphs, but their widespread use raises privacy concerns as graph data can contain personal or sensitive information. Differentially private GNN models have been recently proposed to p ...

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 ...

Statistical (machine-learning, ML) models are more and more often used in computational chemistry as a substitute to more expensive ab initio and parametrizable methods. While the ML algorithms are capable of learning physical laws implicitly from data, ad ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Digital twins are virtual models of physical objects or systems that enable real-time monitoring and analysis. In the ﬁeld of stone masonry buildings, digital twins can be used to assess damage, predict maintenance needs, and opti- mize building performanc ...

In this thesis, we conduct a comprehensive investigation into structural instabilities of both elastic and magneto-elastic beams and shells, resulting in a creative proposal to design a programmable braille reader. Methodologically, we combine numerical si ...

Decentralized learning is appealing as it enables the scalable usage of large amounts of distributed data and resources (without resorting to any central entity), while promoting privacy since every user minimizes the direct exposure of their data. Yet, wi ...

Electric vehicles (EVs) are becoming more popular due to environmental consciousness. The limited availability of charging stations (CSs), compared to the number of EVs on the road, has led to increased range anxiety and a higher frequency of CS queries du ...

The probability of detecting technosignatures (i.e., evidence of technological activity beyond Earth) increases with their longevity, or the time interval over which they manifest. Therefore, the assumed distribution of longevities has some bearing on the ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

Atomistic simulations performed with a family of model potential with tunable hardness have proven to be a great tool for advancing the understanding of wear processes at the asperity level. They have been instrumental in finding a critical length scale, w ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

Data-Aware Privacy-Preserving Machine Learning

Chat with Graph Search

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

White adipose tissue distribution and amount are associated with increased white matter connectivity

The phase-space distribution of the M 81 satellite system

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

ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees

Topics in statistical physics of high-dimensional machine learning

Encoding quantum-chemical knowledge into machine-learning models of complex molecular properties

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Exploiting the Signal-Leak Bias in Diffusion Models

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Digital Twins of Stone Masonry Buildings for Damage Assessment

Instabilities in Elastic and Magneto-Elastic Beams and Shells: from Shell Buckling to the Design of a Programmable Braille Reader

The Privacy Power of Correlated Noise in Decentralized Learning

A Privacy-Preserving Querying Mechanism with High Utility for Electric Vehicles

Technosignatures Longevity and Lindy's Law

Extensions of Peer Prediction Incentive Mechanisms

A story of two transitions: From adhesive to abrasive wear and from ductile to brittle regime

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination