Publication

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

Publications associées (71)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Pierre Vandergheynst, Xavier Bresson, Michaël Defferrard

In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or wor ...

2016

Graph-based denoising for time-varying point clouds

Pierre Vandergheynst, Johann Paratte, Yann Mikaël Schoenenberger

Noisy 3D point clouds arise in many applications. They may be due to errors when creating a 3D model from images or simply to imprecise depth sensors. Point clouds can be given geometrical structure using graphs created from the similarity information betw ...

2015

Downsampling of Signals on Graphs Via Maximum Spanning Trees

Quy Ha Nguyen, Minh Do

Downsampling of signals living on a general weighted graph is not as trivial as of regular signals where we can simply keep every other samples. In this paper we propose a simple, yet effective downsampling scheme in which the underlying graph is approxima ...

Ieee-Inst Electrical Electronics Engineers Inc2015

Structured Auto-Encoder with application to Music Genre Recognition

Michaël Defferrard

In this work, we present a technique that learns discriminative audio features for Music Information Retrieval (MIR). The novelty of the proposed technique is to design auto-encoders that make use of data structures to learn enhanced sparse data representa ...

2015

Laplacian Matrix Learning for Smooth Graph Signal Representation

Pascal Frossard, Pierre Vandergheynst, Xiaowen Dong

The construction of a meaningful graph plays a crucial role in the emerging field of signal processing on graphs. In this paper, we address the problem of learning graph Laplacians, which is similar to learning graph topologies, such that the input data fo ...

2015

On grids in topological graphs

János Pach

A topological graph G is a graph drawn in the plane with vertices represented by points and edges represented by continuous arcs connecting the vertices. If every edge is drawn as a straight-line segment, then G is called a geometric graph. A k-grid in a t ...

Elsevier Science Bv2014

Privacy and Dynamics of Social Networks

Pedram Pedarsani

Over the past decade, investigations in different fields have focused on studying and understanding real networks, ranging from biological to social to technological. These networks, called complex networks, exhibit common topological features, such as a h ...

EPFL2013

Parametric dictionary learning for graph signals

Pascal Frossard, David Shuman

We propose a parametric dictionary learning algorithm to design structured dictionaries that sparsely represent graph signals. We incorporate the graph structure by forcing the learned dictionaries to be concatenations of subdictionaries that are polynomia ...

2013

Segmenting Planar Superpixel Adjacency Graphs w.r.t. Non-planar Superpixel Affinity Graphs

Engin Türetken

We address the problem of segmenting an image into a previously unknown number of segments from the perspective of graph partitioning. Specifically, we consider minimum multicuts of superpixel affinity graphs in which all affinities between non-adjacent su ...

2013

DIRECTFN: Fully Numerical Algorithms for High Precision Computation of Singular Integrals in Galerkin SIE Methods

Juan Ramon Mosig

Fully numerical schemes are presented for high precision computations of the four-dimensional integrals arising in Galerkin surface integral equation formulations. More specifically, the focal point of this paper is the singular integrals for coincident, e ...

Institute of Electrical and Electronics Engineers2013