Concept
Perfect graph
Related publications (96)
Molecular hypergraph neural networks
Philippe Schwaller, Junwu Chen
Graph neural networks (GNNs) have demonstrated promising performance across various chemistry-related tasks. However, conventional graphs only model the pairwise connectivity in molecules, failing to adequately represent higher order connections, such as m ...
Aip Publishing2024fGOT: Graph Distances Based on Filters and Optimal Transport
Pascal Frossard, Mireille El Gheche, Hermina Petric Maretic, Giovanni Chierchia
Graph comparison deals with identifying similarities and dissimilarities between graphs. A major obstacle is the unknown alignment of graphs, as well as the lack of accurate and inexpensive comparison metrics. In this work we introduce the filter graph dis ...
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE2022Graph Neural Networks With Lifting-Based Adaptive Graph Wavelets
Pascal Frossard, Chenglin Li, Mingxing Xu
Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid transforms and cannot adapt to signals residing on graphs ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022Graph signal processing tailored for subgraph focus and community structure
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, ...
EPFL2022Representing graphs through data with learning and optimal transport
Graphs offer a simple yet meaningful representation of relationships between data. Thisrepresentation is often used in machine learning algorithms in order to incorporate structuralor geometric information about data. However, it can also be used in an inv ...
EPFL2021Figlearn: Filter And Graph Learning Using Optimal Transport
Pascal Frossard, Mireille El Gheche, Matthias Minder, Zahra Farsijani
In many applications, a dataset can be considered as a set of observed signals that live on an unknown underlying graph structure. Some of these signals may be seen as white noise that has been filtered on the graph topology by a graph filter. Hence, the k ...
IEEE2021Efficient Streaming Subgraph Isomorphism with Graph Neural Networks
Karl Aberer, Quoc Viet Hung Nguyen, Chi Thang Duong, Trung-Dung Hoang
Queries to detect isomorphic subgraphs are important in graph-based data management. While the problem of subgraph isomorphism search has received considerable attention for the static setting of a single query, or a batch thereof, existing approaches do n ...
ASSOC COMPUTING MACHINERY2021Holistic, Efficient, and Real-time Cleaning of Heterogeneous Data
Styliani Asimina Giannakopoulou
Data cleaning has become an indispensable part of data analysis due to the increasing amount of dirty data. Data scientists spend most of their time preparing dirty data before it can be used for data analysis. Existing solutions that attempt to automate t ...
EPFL2021Avoiding long Berge cycles: the missing casesk=r+1 andk=r+2
The maximum size of anr-uniform hypergraph without a Berge cycle of length at leastkhas been determined for allk >= r+ 3 by Furedi, Kostochka and Luo and fork
2020Improved Ramsey-type results for comparability graphs
Istvan Tomon, Dániel József Korándi
Several discrete geometry problems are equivalent to estimating the size of the largest homogeneous sets in graphs that happen to be the union of few comparability graphs. An important observation for such results is that if G is an n-vertex graph that is ...
CAMBRIDGE UNIV PRESS2020