On sums of graph eigenvalues

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (30)

Nature vs. Nurture: Feature vs. Structure for Graph Neural Networks

Karl Aberer, Quoc Viet Hung Nguyen, Thành Tâm Nguyên, Chi Thang Duong

Graph neural networks take node features and graph structure as input to build representations for nodes and graphs. While there are a lot of focus on GNN models, understanding the impact of node features and graph structure to GNN performance has received ...

ELSEVIER2022

SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators

Nathanaël Perraudin, Andreas Loukas, Karolis Martinkus

We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral conditioning allows for direct model ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

On the robustness of the metric dimension of grid graphs to adding a single edge

Patrick Thiran, Gergely Odor, Satvik Mehul Mashkaria

The metric dimension (MD) of a graph is a combinatorial notion capturing the minimum number of landmark nodes needed to distinguish every pair of nodes in the graph based on graph distance. We study how much the MD can increase if we add a single edge to t ...

2022

Graph signal processing tailored for subgraph focus and community structure

Miljan Petrovic

Community structure in graph-modeled data appears in a range of disciplines that comprise network science. Its importance relies on the influence it bears on other properties of graphs such as resilience, or prediction of missing connections. Nevertheless, ...

EPFL2022

Generalised Implicit Neural Representations

Pierre Vandergheynst

We consider the problem of learning implicit neural representations (INRs) for signals on non-Euclidean domains. In the Euclidean case, INRs are trained on a discrete sampling of a signal over a regular lattice. Here, we assume that the continuous signal e ...

2022

Incompleteness of graph neural networks for points clouds in three dimensions

Michele Ceriotti, Sergey Pozdnyakov

Graph neural networks (GNN) are very popular methods in machine learning and have been applied very successfully to the prediction of the properties of molecules and materials. First-order GNNs are well known to be incomplete, i.e. there exist graphs that ...

IOP Publishing Ltd2022

Graph Embedding for Retrieval

Chi Thang Duong

Information retrieval (IR) systems such as search engines are important for people to find what they need among the tremendous amount of data available in their organization or on the Internet. These IR systems enable users to search in a large data collec ...

EPFL2022

A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models

Saber Salehkaleybar, Negar Kiyavash, Ehsan Mokhtarian

We study experiment design for unique identification of the causal graph of a system where the graph may contain cycles. The presence of cycles in the structure introduces major challenges for experiment design as, unlike acyclic graphs, learning the skele ...

2023

Annihilation Filter Approach For Estimating Graph Dynamics From Diffusion Processes

Pascal Frossard, Arun Venkitaraman

We propose an approach for estimating graph diffusion processes using annihilation filters from a finite set of observations of the diffusion process made at regular intervals. Our approach is based on the key observation that a graph diffusion process can ...

IEEE2022

Distributed Graph Learning With Smooth Data Priors

Pascal Frossard, Isabela Cunha Maia Nobre, Mireille El Gheche

Graph learning is often a necessary step in processing or representing structured data, when the underlying graph is not given explicitly. Graph learning is generally performed centrally with a full knowledge of the graph signals, namely the data that live ...

IEEE2022

Page 2 sur 2