Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Achten, Sonny, Tonin, Francesco, Patrinos, Panagiotis, Suykens, Johan A. K.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917639542013952
author Achten, Sonny
Tonin, Francesco
Patrinos, Panagiotis
Suykens, Johan A. K.
author_facet Achten, Sonny
Tonin, Francesco
Patrinos, Panagiotis
Suykens, Johan A. K.
contents We present a deep Graph Convolutional Kernel Machine (GCKM) for semi-supervised node classification in graphs. The method is built of two main types of blocks: (i) We introduce unsupervised kernel machine layers propagating the node features in a one-hop neighborhood, using implicit node feature mappings. (ii) We specify a semi-supervised classification kernel machine through the lens of the Fenchel-Young inequality. We derive an effective initialization scheme and efficient end-to-end training algorithm in the dual variables for the full architecture. The main idea underlying GCKM is that, because of the unsupervised core, the final model can achieve higher performance in semi-supervised node classification when few labels are available for training. Experimental results demonstrate the effectiveness of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2301_13764
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
Achten, Sonny
Tonin, Francesco
Patrinos, Panagiotis
Suykens, Johan A. K.
Machine Learning
We present a deep Graph Convolutional Kernel Machine (GCKM) for semi-supervised node classification in graphs. The method is built of two main types of blocks: (i) We introduce unsupervised kernel machine layers propagating the node features in a one-hop neighborhood, using implicit node feature mappings. (ii) We specify a semi-supervised classification kernel machine through the lens of the Fenchel-Young inequality. We derive an effective initialization scheme and efficient end-to-end training algorithm in the dual variables for the full architecture. The main idea underlying GCKM is that, because of the unsupervised core, the final model can achieve higher performance in semi-supervised node classification when few labels are available for training. Experimental results demonstrate the effectiveness of the proposed framework.
title Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
topic Machine Learning
url https://arxiv.org/abs/2301.13764