Nested Dichotomies with probability sets for multi-class classification

Gen Yang (1, 2) , Sébastien Destercke (1, 2) , Marie-Hélène Masson (1, 2)

1 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]
2 Labex MS2T - Laboratoire d'Excellence "Maîtrise des Systèmes de Systèmes Technologiques"

Binary decomposition techniques transform a multi-class problem into several simpler binary problems. In such techniques, a classical issue is to ensure the consistency between the binary as- sessments of conditional probabilities. Nested dichotomies, which consider tree-shaped decomposition, do not suffer from this issue. Yet, a wrong probability estimate in the tree can strongly biase the results and provide wrong predictions. To overcome this issue, we consider in this paper imprecise nested dichotomies, in which binary probabilities become imprecise. We show in experiments that the approach has many advantages: it provides cautious inferences when only little information is available, and allows to make efficient computations with imprecise probabilities even when considering generic cost functions.

Mots clés: nested dichotomies; cost sensitive; classification; imprecise probabilities

Domaines: Machine Learning [stat.ML]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]

Gen Yang, Sébastien Destercke, Marie-Hélène Masson. Nested Dichotomies with probability sets for multi-class classification. European Conference on Artificial Intelligence (ECAI 2014), Aug 2014, Prague, Czech Republic. pp.363-368. ⟨hal-01059865⟩