Imperial College London

ProfessorMichaelBronstein

Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition
 
 
 
//

Contact

 

m.bronstein Website

 
 
//

Location

 

569Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Monti:2018:10.1109/DSW.2018.8439897,
author = {Monti, F and Otness, K and Bronstein, MM},
doi = {10.1109/DSW.2018.8439897},
pages = {225--228},
title = {MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORK for DIRECTED GRAPHS},
url = {http://dx.doi.org/10.1109/DSW.2018.8439897},
year = {2018}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - © 2018 IEEE. Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning community. Many of such techniques explore the analogy between the graph Laplacian eigenvectors and the classical Fourier basis, allowing to formulate the convolution as a multiplication in the spectral domain. One of the key drawback of spectral CNNs is their explicit assumption of an undirected graph, leading to a symmetric Laplacian matrix with orthogonal eigendecomposition. In this work we propose MotifNet, a graph CNN capable of dealing with directed graphs by exploiting local graph motifs. We present experimental evidence showing the advantage of our approach on real data.
AU - Monti,F
AU - Otness,K
AU - Bronstein,MM
DO - 10.1109/DSW.2018.8439897
EP - 228
PY - 2018///
SP - 225
TI - MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORK for DIRECTED GRAPHS
UR - http://dx.doi.org/10.1109/DSW.2018.8439897
ER -