TY - GEN
T1 - MOTIFNET
T2 - 2018 IEEE Data Science Workshop, DSW 2018
AU - Monti, Federico
AU - Otness, Karl
AU - Bronstein, Michael M.
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/8/17
Y1 - 2018/8/17
N2 - 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.
AB - 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.
KW - Directed Graphs
KW - Geometric Deep Learning
KW - Graph Convolutional Neural Networks
KW - Graph Motifs
UR - http://www.scopus.com/inward/record.url?scp=85053154620&partnerID=8YFLogxK
U2 - 10.1109/DSW.2018.8439897
DO - 10.1109/DSW.2018.8439897
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85053154620
SN - 9781538644102
T3 - 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings
SP - 225
EP - 228
BT - 2018 IEEE Data Science Workshop, DSW 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 June 2018 through 6 June 2018
ER -