Bottom-up generative modeling of tree-structured data

Authors:
Davide Bacciu;Alessio Micheli;Alessandro Sperduti
Affiliations:
Dipartimento di Informatica, Università di Pisa;Dipartimento di Informatica, Università di Pisa;Dipartimento di Matematica Pura e Applicata, Università di Padova
Venue:
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: theory and algorithms - Volume Part I
Year:
2010

Citing 7
Cited 2

Mixed Memory Markov Models: Decomposing Complex Stochastic Processes as Mixtures of Simpler Ones

Machine Learning
Hidden Tree Markov Models for Document Image Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Parsing with Probabilistic Strictly Locally Testable Tree Languages

IEEE Transactions on Pattern Analysis and Machine Intelligence
Report on the XML mining track at INEX 2005 and INEX 2006: categorization and clustering of XML documents

ACM SIGIR Forum
Wavelet-based statistical signal processing using hidden Markovmodels

IEEE Transactions on Signal Processing
Computational methods for hidden Markov tree models-an application to wavelet trees

IEEE Transactions on Signal Processing
A general framework for adaptive processing of data structures

IEEE Transactions on Neural Networks

Tree Echo State Networks

Neurocomputing
An input-output hidden Markov model for tree transductions

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a compositional probabilistic model for treestructured data that defines a bottom-up generative process from the leaves to the root of a tree. Contextual state transitions are introduced from the joint configuration of the children to the parent nodes, allowing hidden states to model the co-occurrence of substructures among the child subtrees. A mixed memory approximation is proposed to factorize the joint transition matrix as a mixture of pairwise transitions. A comparative experimental analysis shows that the proposed approach is able to better model deep structures with respect to top-down approaches.