Discrete and Continuous Deep Residual Learning over Graphs

Pedro Avelar, Anderson Tavares, Marco Gori, Luís Lamb

Abstract

We propose the use of continuous residual modules for graph kernels in Graph Neural Networks. We show how both discrete and continuous residual layers allow for more robust training, being that continuous residual layers are applied by integrating through an Ordinary Differential Equation (ODE) solver to produce their output. We experimentally show that these modules achieve better results than the ones with non-residual modules when multiple layers are used, thus mitigating the low-pass filtering effect of Graph Convolutional Network-based models. Finally, we discuss the behaviour of discrete and continuous residual layers, pointing out possible domains where they could be useful by allowing more predictable behaviour under dynamic times of computation.

Download


Paper Citation


in Harvard Style

Avelar P., Tavares A., Gori M. and Lamb L. (2021). Discrete and Continuous Deep Residual Learning over Graphs.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 119-131. DOI: 10.5220/0010231501190131


in Bibtex Style

@conference{icaart21,
author={Pedro Avelar and Anderson Tavares and Marco Gori and Luís Lamb},
title={Discrete and Continuous Deep Residual Learning over Graphs},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={119-131},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010231501190131},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Discrete and Continuous Deep Residual Learning over Graphs
SN - 978-989-758-484-8
AU - Avelar P.
AU - Tavares A.
AU - Gori M.
AU - Lamb L.
PY - 2021
SP - 119
EP - 131
DO - 10.5220/0010231501190131