Publications associées à Irreducible network backbones: unbiased graph filtering via maximum entropy

Publications associées (36)

Quantifying the biomimicry gap in biohybrid robot-fish pairs

Biohybrid systems in which robotic lures interact with animals have become compelling tools for probing and identifying the mechanisms underlying collective animal behavior. One key challenge lies in the transfer of social interaction models from simulatio ...

2024

Validating Automatic Speech Recognition and Understanding for Pre-Filling Radar Labels-Increasing Safety While Reducing Air Traffic Controllers' Workload

Juan Pablo Zuluaga Gomez

Automatic speech recognition and understanding (ASRU) for air traffic control (ATC) has been investigated in different ATC environments and applications. The objective of this study was to quantify the effect of ASRU support for air traffic controllers (AT ...

2023

Machine Learning Security in Industry: A Quantitative Survey

Kathrin Grosse

Despite the large body of academic work on machine learning security, little is known about the occurrence of attacks on machine learning systems in the wild. In this paper, we report on a quantitative study with 139 industrial practitioners. We analyze at ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Partial Information Sharing Over Social Learning Networks

Ali H. Sayed, Virginia Bordignon

This work addresses the problem of sharing partial information within social learning strategies. In social learning, agents solve a distributed multiple hypothesis testing problem by performing two operations at each instant: first, agents incorporate inf ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Bayesian Error-in-Variables Models for the Identification of Distribution Grids

Giancarlo Ferrari Trecate, Pulkit Nahata, Jean-Sébastien Hubert Brouillon

The increasing integration of renewable energy requires a good model of the existing power distribution infrastructure, represented by its admittance matrix. However, a reliable estimate may either be missing or quickly become obsolete, as distribution gri ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Reinforced Attention for Few-Shot Learning and Beyond

Tong Zhang

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images. In this paper, we propose to equip the backbone network with an attention agent, whi ...

IEEE COMPUTER SOC2021

Localizing Traffic Differentiation

Aikaterini Argyraki, Pavlos Nikolopoulos, Muhammad Abdullah, Zeinab Shmeis

Network neutrality is important for users, content providers, policymakers, and regulators interested in understanding how network providers differentiate performance. When determining whether a network differentiates against certain traffic, it is importa ...

2023

True scale-free networks hidden by finite size effects

Andrea Rinaldo, Amos Maritan, Samir Suweis

We analyze about 200 naturally occurring networks with distinct dynamical origins to formally test whether the commonly assumed hypothesis of an underlying scale-free structure is generally viable. This has recently been questioned on the basis of statisti ...

National Academy of Sciences2021

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Elisabetta Cornacchia

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

EPFL2023

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Martin Jaggi, Sebastian Urban Stich

In distributed optimization, parameter updates from the gradient computing node devices have to be aggregated in every iteration on the orchestrating server. When these updates are sent over an arbitrary commodity network, bandwidth and latency can be limi ...

MICROTOME PUBLISHING2021

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021

Atomic subgraphs and the statistical mechanics of networks

Sofia Charlotta Olhede

We develop random graph models where graphs are generated by connecting not only pairs of vertices by edges, but also larger subsets of vertices by copies of small atomic subgraphs of arbitrary topology. This allows for the generation of graphs with extens ...

2021

Social Learning Under Inferential Attacks

Ali H. Sayed, Stefan Vlaski, Virginia Bordignon, Konstantinos Ntemos

A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at driving the network beliefs to the wrong hypothesis. The adversaries a ...

IEEE2021

The structural connectome and motor recovery after stroke: predicting natural recovery

Jean-Philippe Thiran, Friedhelm Christoph Hummel, Gabriel Girard, Takuya Morishita, Maximilian Jonas Wessel, Chang-Hyun Park, Elena Beanato, Philip Egger, Philipp Johannes Koch, Giorgia Giulia Evangelista

Stroke patients vary considerably in terms of outcomes: some patients present ‘natural’ recovery proportional to their initial impairment (fitters), while others do not (non-fitters). Thus, a key challenge in stroke rehabilitation is to identify individual ...

2021

On Representation Learning for Scientific News Articles Using Heterogeneous Knowledge Graphs

Karl Aberer, Panagiotis Smeros, Angeliki Romanou

In the era of misinformation and information inflation, the credibility assessment of the produced news is of the essence. However, fact-checking can be challenging considering the limited references presented in the news. This challenge can be transcended ...

ASSOC COMPUTING MACHINERY2021

A Stepwise Domain Adaptive Segmentation Network With Covariate Shift Alleviation for Remote Sensing Imagery

Yinlin Hu, Yunpeng Li

Semantic segmentation for remote sensing images (RSI) is critical for the Earth monitoring system. However, the covariate shift between RSI datasets under different capture conditions cannot be alleviated by directly using the unsupervised domain adaptatio ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

NICEpath: Finding metabolic pathways in large networks through atom-conserving substrate-product pairs

Vassily Hatzimanikatis, Jasmin Maria Hafner

Motivation: Finding biosynthetic pathways is essential for metabolic engineering of organisms to produce chemicals, biodegradation prediction of pollutants and drugs, and for the elucidation of bioproduction pathways of secondary metabolites. A key step in ...

Oxford University Press2021

Morphology and morphodynamics of braided rivers: an experimental investigation

Daniel Vito Papa

Braided rivers form some of the most fascinating fluvial patterns found on Earth. They are identifiable by their unique morphology of complex networks of intertwined channels that spread across wide floodplains. Detailed knowledge of their dynamics is need ...

EPFL2020

Mesoscopic description of hippocampal replay and metastability in spiking neural networks with short-term plasticity

Tilo Schwalger, Valentin Marc Schmutz

Bottom-up models of functionally relevant patterns of neural activity provide an explicit link between neuronal dynamics and computation. A prime example of functional activity patterns are propagating bursts of place-cell activities called hippocampal rep ...

PUBLIC LIBRARY SCIENCE2022

Large-scale traffic signal control and multimodal network design

Dimitrios Tsitsokas

Traffic congestion constitutes one of the most frequent, yet challenging, problems to address in the urban space. Caused by the concentration of population, whose mobility needs surpass the serving capacity of urban networks, congestion cannot be resolved ...

EPFL2022