Detecting Irrelevant subtrees to improve probabilistic learning from tree-structured data

Amaury Habrard (1) , Marc Bernard (2) , Marc Sebban (2)

1 LIF - Laboratoire d'informatique Fondamentale de Marseille - UMR 6166
2 LHC - Laboratoire Hubert Curien

In front of the large increase of the available amount of structured data (such as XML documents), many algorithms have emerged for dealing with tree-structured data. In this article, we present a probabilistic approach which aims at a posteriori pruning noisy or irrelevant subtrees in a set of trees. The originality of this approach, in comparison with classic data reduction techniques, comes from the fact that only a part of a tree (i.e. a subtree) can be deleted, rather than the whole tree itself. Our method is based on the use of confidence intervals, on a partition of subtrees, computed according to a given probability distribution. We propose an original approach to assess these intervals on tree-structured data and we experimentally show its interest in the presence of noise.

Mots clés: data reduction; tree-structured data; noisy data; stochastic tree automata

Domaines: Apprentissage [cs.LG]

Amaury Habrard, Marc Bernard, Marc Sebban. Detecting Irrelevant subtrees to improve probabilistic learning from tree-structured data. Fundamenta Informaticae, 2005, 66 (1,2), pp.103-130. ⟨hal-00369445⟩