We study the problem of classifying data in a given taxonomy when classifications associated with multiple and/or partial paths are allowed. We introduce an incremental algorithm using a linear-threshold classifier at each node of the taxonomy. These classifiers are trained and evaluated in a hierarchical top-down fashion. We then define a hierachical and parametric data model and prove a bound on the probability that our algorithm guesses the wrong multilabel for a random instance compared to the same probability when the true model parameters are known. Our bound decreases exponentially with the number of training examples and depends in a detailed way on the interaction between the process parameters and the taxonomy structure. Preliminary experiments on real-world data provide support to our theoretical results.
CITATION STYLE
Cesa-Bianchi, N., Conconi, A., & Gentile, C. (2004). Regret bounds for hierarchical classification with linear-threshold functions. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3120, pp. 93–108). Springer Verlag. https://doi.org/10.1007/978-3-540-27819-1_7
Mendeley helps you to discover research relevant for your work.