Publications related to Decision Learning and Adaptation Over Multi-Task Networks

Related publications (50)

Graph Neural Networks With Adaptive Structures

Graph neural networks (GNNs) have made significant progress in various machine learning tasks. Despite their success, many existing GNN models are shown to be vulnerable to adversarial attacks, creating a stringent need to build robust GNN architectures. I ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2025

Intelligent and Self-Driving Microscopy of Protein Aggregation in Neurodegenerative Diseases

Khalid Ashraf Mohie Ibrahim

Neurodegenerative diseases, such as Alzheimer's, Parkinson's, and Huntington's, afflict tens of millions of patients worldwide. They are characterized by protein aggregation and progressive neuronal loss, leading to cognitive and motor impairments, and ult ...

EPFL2025

Robust and Personalized Federated Learning: Handling Data Corruption and Heterogeneity

Ljubomir Rokvic

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling collaborative model training across decentralized devices while preserving data privacy. However, FL's success is highly contingent on the quality and integrity ...

EPFL2025

Unveiling the complexity of learning and decision-making

Wei-Hsiang Lin

Reinforcement learning (RL) is crucial for learning to adapt to new environments. In RL, the prediction error is an important component that compares the expected and actual rewards. Dopamine plays a critical role in encoding these prediction errors. In my ...

EPFL2024

Safe Deep Neural Networks

Kyle Michael Matoba

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

EPFL2024

Adaptive Interface-Pinns (Adai-Pinns) for Transient Diffusion: Applications to Forward and Inverse Problems in Heterogeneous Media

Brice Tanguy Alphonse Lecampion

We model transient diffusion in heterogeneous materials using a novel physics-informed neural networks framework (PINNs) termed Adaptive interface physics-informed neural networks or AdaI-PINNs (Roy et al. arXiv preprint arXiv:2406.04626, 2024). AdaI-PINNs ...

Elsevier BV2025

Partial discharge localization in power transformer tanks using machine learning methods

Farhad Rachidi-Haeri, Marcos Rubinstein, Hamidreza Karami

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

Nature Publishing Group2024

NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability

Alexandre Massoud Alahi, Krishna Kanth Nakka

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this approach and intr ...

IEEE2025

Learning transferable land cover semantics for open vocabulary interactions with remote sensing images

Devis Tuia, Javiera Francisca Castillo Navarro, Valérie Zermatten

Why should we confine land cover classes to rigid and arbitrary definitions? Land cover mapping is a central task in remote sensing image processing, but the rigorous class definitions can sometimes restrict the transferability of annotations between datas ...

2025

Optimal regimes for algorithm-assisted human decision-making

Mats Julius Stensrud, Aaron Leor Sarvet, Julien David Laurendeau

We consider optimal regimes for algorithm-assisted human decision-making. Such regimes are decision functions of measured pre-treatment variables and, by leveraging natural treatment values, enjoy a superoptimality property whereby they are guaranteed to o ...

2024

Non-regular Inference: Universal Inference and Discrete Profiling

Timmy Rong Tian Tse

Non-regular or irregular statistical problems are those that do not satisfy a set of standard regularity conditions that allow useful theoretical properties of inferential procedures to be proven. Non-regular problems are prevalent; a classical example is ...

EPFL2025

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Revealing Brain and Spinal Cord Functional Networks by Block-Structured Graph Laplacian Mixture Models

Pascal Frossard, Dimitri Nestor Alice Van De Ville, Ilaria Ricchi, Ekansh Sareen, William Cappelletti

The Graph Laplacian Mixture Model (GLMM) allows to infer multiple underlying graph structures from multivariate time series data. Given its effectiveness in identifying brain states from brain activity measured by functional magnetic resonance imaging (fMR ...

IEEE2025

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

Jean-Paul Richard Kneib, Emma Elizabeth Tolley, Michele Bianco, Tianyue Chen

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 ...

Oxford Univ Press2024

Deep learning approach for identification of Hii regions during reionization in 21-cm observations – III. image recovery

Michele Bianco, Tianyue Chen, Shreyam Parth Krishna

The low-frequency component of the upcoming Square Kilometre Array Observatory (SKA-Low) will be sensitive enough to construct 3D tomographic images of the 21-cm signal distribution during reionization. However, foreground contamination poses challenges fo ...

Oxford University Press (OUP)2025

T-matrix representation of optical scattering response: Suggestion for a data format

Karim Achouri

The transition matrix, frequently abbreviated as T-matrix, contains the complete information in a linear approximation of how a spatially localized object scatters an incident field. The T-matrix is used to study the scattering response of an isolated obje ...

2025

An aircraft assembly process formalism and verification method based on semantic modeling and MBSE

Dimitrios Kyritsis, Jinzhi Lu, Xiaochen Zheng

The aircraft assembly system is highly complex involving different stakeholders from multiple domains. The design of such a system requires comprehensive consideration of various industrial scenarios aiming to optimize key performance indicators. Tradition ...

Elsevier Sci Ltd2024

Device-Free Floor-Scale Human Detection With Indoor LTE Antennas

Andreas Peter Burg, Sitian Li

This paper introduces a novel method for device-free human detection by leveraging existing wireless communication signals from 4G-long-term evolution (4G-LTE) systems. By utilizing the pervasive 4G-LTE signals, our approach enhances the efficiency and cov ...

2025

Towards practical reinforcement learning for tokamak magnetic control

Federico Alberto Alfredo Felici, Jonas Buchli, Cristian Galperti

Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinem ...

Elsevier Science Sa2024

Event-based sensing for efficient processing in low-power IoT platforms

Silvio Zanoli

Modern IoT platforms implement a plethora of techniques for both improving performance and energy efficiency. Because of this, the leading cause of energy consumption in IoT devices is moving from raw computation to data acquisition, storage, and transmiss ...

EPFL2025