Publications related to Learning Privacy from Visual Entities

Related publications (16)

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model

Matthieu Wyart, Leonardo Petrini, Alessandro Favero, Francesco Cagnetta, Umberto Maria Tomasini

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representatio ...

American Physical Society2024

Maximum Independent Set: Self-Training through Dynamic Programming

Volkan Cevher, Grigorios Chrysos, Efstratios Panteleimon Skoulakis

This work presents a graph neural network (GNN) framework for solving the maximum independent set (MIS) problem, inspired by dynamic programming (DP). Specifically, given a graph, we propose a DP-like recursive algorithm based on GNNs that firstly construc ...

2023

Quantization for Decentralized Learning Under Subspace Constraints

Ali H. Sayed, Stefan Vlaski, Roula Nassif

In this article, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces. This constrained fo ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Metric learning for kernel ridge regression: assessment of molecular similarity

Anne-Clémence Corminboeuf, Friedrich Eisenbrand, Raimon Fabregat I De Aguilar-Amat, Puck Elisabeth van Gerwen, Matthieu Nicolas Haeberle

Supervised and unsupervised kernel-based algorithms widely used in the physical sciences depend upon the notion of similarity. Their reliance on pre-defined distance metrics-e.g. the Euclidean or Manhattan distance-are problematic especially when used in c ...

IOP Publishing Ltd2022

Motif Cut Sparsifiers

Mikhail Kapralov, Jakab Tardos, Mikhail Makarov

A motif is a frequently occurring subgraph of a given directed or undirected graph G (Milo et al.). Motifs capture higher order organizational structure of G beyond edge relationships, and, therefore, have found wide applications such as in graph clusterin ...

IEEE COMPUTER SOC2022

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation

Pascal Fua, Mathieu Salzmann, Helge Jochen Rhodin, Sina Honari, Victor Constantin

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich lat ...

2022

Representation Learning for Multi-relational Data

Eda Bayram

Recent years have witnessed a rise in real-world data captured with rich structural information that can be better depicted by multi-relational or heterogeneous graphs. However, research on relational representation learning has so far mostly focused on th ...

EPFL2021

Approaching Ontology Alignment through Representation Learning to Bridge the Semantic Gap in Engineering Applications

Prodromos Kolyvakis

The current information landscape is characterised by a vast amount of relatively semantically homogeneous, when observed in isolation, data silos that are, however, drastically semantically fragmented when considered as a whole. Within each data silo, inf ...

EPFL2020

Graph Signal Processing : Sparse Representation and Applications

Ntorina Thanou

Over the past few decades we have been experiencing an explosion of information generated by large networks of sensors and other data sources. Much of this data is intrinsically structured, such as traffic evolution in a transportation network, temperature ...

EPFL2016

CP-CHARM: Segmentation-Free Image Classification Made Accessible

Virginie Sophie Uhlmann

Background: Automated classification using machine learning often relies on features derived from segmenting individual objects, which can be difficult to automate. WND-CHARM is a previously developed classification algorithm in which features are computed ...

2016

Graph Embedded Nonparametric Mutual Information For Supervised Dimensionality Reduction

Nikolaos Arvanitopoulos Darginis

In this paper, we propose a novel algorithm for dimensionality reduction that uses as a criterion the mutual information (MI) between the transformed data and their cor- responding class labels. The MI is a powerful criterion that can be used as a proxy to ...

Institute of Electrical and Electronics Engineers2015

Joint Power Allocation and Path Selection for Multi-Hop Noncoherent Decode and Forward UWB Communications

Marco Mondelli, Xiaoli Ma

With the aim of extending the coverage and improving the performance of impulse radio ultra-wideband (UWB) systems, this paper focuses on developing a novel single differential encoded decode and forward (DF) non-cooperative relaying scheme (NCR). To favor ...

Ieee-Inst Electrical Electronics Engineers Inc2014

SVM Active Learning Approach for Image Classification Using Spatial Information

Devis Tuia

In the last few years, active learning has been gaining growing interest in the remote sensing community in optimizing the process of training sample collection for supervised image classification. Current strategies formulate the active learning problem i ...

Ieee-Inst Electrical Electronics Engineers Inc2014

Learning Discriminative Features and Structured Models for Segmentation in Microscopy and Natural Images

Aurélien Lucchi

Segmenting images is a significant challenge that has drawn a lot of attention from different fields of artificial intelligence and has many practical applications. One such challenge addressed in this thesis is the segmentation of electron microscope (EM) ...

EPFL2013

Learning Near-optimal Decision Rules for Energy Efficient Building Control

Colin Neil Jones

Recent studies suggest that advanced optimization based control methods such as model predictive control (MPC) can increase energy efficiency of buildings. However, adoption of these methods by industry is still slow, as building operators are used to work ...

2012

Unsupervised Extraction of Audio-Visual Objects

Pierre Vandergheynst, Anna Llagostera Casanovas

We propose a novel method to automatically detect and extract the video modality of the sound sources that are present in a scene. For this purpose, we first assess the synchrony between the moving objects captured with a video camera and the sounds record ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2011