A preliminary empirical comparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domains

Authors:
Alessio Micheli;Filippo Portera;Alessandro Sperduti
Affiliations:
Dipartimento di Informatica, Universití di Pisa, Pisa, Italia;Dipartimento di Matematica Pura ed Applicata, Universití degli Studi di Padova, Padova, Italia;Dipartimento di Matematica Pura ed Applicata, Universití degli Studi di Padova, Padova, Italia
Venue:
Neurocomputing
Year:
2005

Citing 10
Cited 6

An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Learning with Recurrent Neural Networks

Learning with Recurrent Neural Networks
Relational Data Mining

Relational Data Mining
Application of Cascade Correlation Networks for Structures toChemistry

Applied Intelligence
Extended Cascade-Correlation for Syntactic and Structural Pattern Recognition

SSPR '96 Proceedings of the 6th International Workshop on Advances in Structural and Syntactical Pattern Recognition
Hidden Tree Markov Models for Document Image Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
The principled design of large-scale recursive neural network architectures--dag-rnns and the protein structure prediction problem

The Journal of Machine Learning Research
A survey of kernels for structured data

ACM SIGKDD Explorations Newsletter
Supervised neural networks for the classification of structures

IEEE Transactions on Neural Networks
Contextual processing of structured data by recursive cascade correlation

IEEE Transactions on Neural Networks

From Hopfield nets to recursive networks to graph machines: numerical machine learning for structured data

Theoretical Computer Science
Fuzzy lattice reasoning (FLR) type neural computation for weighted graph partitioning

Neurocomputing
Neural network for graphs: a contextual constructive approach

IEEE Transactions on Neural Networks
Fuzzy ARTMAP Prediction of Biological Activities for Potential HIV-1 Protease Inhibitors Using a Small Molecular Data Set

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
A new neural network model for contextual processing of graphs

WIRN'05 Proceedings of the 16th Italian conference on Neural Nets
Tree Echo State Networks

Neurocomputing

Quantified Score

Hi-index	0.02

Visualization

Abstract

The aim of this paper is to start a comparison between recursive neural networks (RecNN) and kernel methods for structured data, specifically support vector regression (SVR) machine using a tree kernel, in the context of regression tasks for trees. Both the approaches can deal directly with a structured input representation and differ in the construction of the feature space from structured data. We present and discuss preliminary empirical results for specific regression tasks involving well-known quantitative structure-activity and quantitative structure-property relationship (QSAR/QSPR) problems, where both the approaches are able to achieve state-of-the-art results.