Skip to main navigation
Skip to search
Skip to main content
Technical University of Munich Home
Help & FAQ
English
Deutsch
Home
Profiles
Research units
Projects
Research output
Equipment
Prizes
Activities
Press/Media
Search by expertise, name or affiliation
Edge Directionality Improves Learning on Heterophilic Graphs
Emanuele Rossi
, Bertrand Charpentier
, Francesco Di Giovanni
, Fabrizio Frasca
,
Stephan Günnemann
, Michael Bronstein
Informatics 26 - Chair of Professorship of Data Analytics and Machine Learning
Imperial College London
Technical University of Munich
University of Cambridge
Research output
:
Contribution to journal
›
Conference article
›
peer-review
17
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Edge Directionality Improves Learning on Heterophilic Graphs'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Learning Improvement
100%
Directed Graph Neural Network
100%
Heterophilic Graphs
100%
Graph Neural Network
66%
Heterophil
66%
Neural Network Model
33%
Deep Learning
33%
Potential Gains
33%
Directed Graph
33%
Large Gain
33%
Undirected Graph
33%
De Facto Standard
33%
Relational Data
33%
Homophily
33%
Correct Use
33%
Real-world Graphs
33%
Complex Method
33%
Message Passing Neural Network
33%
GraphSAGE
33%
Spectral Graph Neural Networks
33%
Weisfeiler-Lehman Test
33%
Computer Science
Directed Graphs
100%
Graph Neural Network
100%
Neural Network
16%
Neural Network Model
16%
Message Passing
16%
New-State
16%
De Facto Standard
16%
Relational Data
16%
Potential Gain
16%
Deep Learning Method
16%