Learning Output Embeddings in Structured Prediction - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... (Working Paper) Year : 2021

Learning Output Embeddings in Structured Prediction

Abstract

A powerful and flexible approach to structured prediction consists in embedding the structured objects to be predicted into a feature space of possibly infinite dimension by means of output kernels, and then, solving a regression problem in this output space. A prediction in the original space is computed by solving a pre-image problem. In such an approach, the embedding, linked to the target loss, is defined prior to the learning phase. In this work, we propose to jointly learn a finite approximation of the output embedding and the regression function into the new feature space. For that purpose, we leverage a priori information on the outputs and also unexploited unsupervised output data, which are both often available in structured prediction problems. We prove that the resulting structured predictor is a consistent estimator, and derive an excess risk bound. Moreover, the novel structured prediction tool enjoys a significantly smaller computational complexity than former output kernel methods. The approach empirically tested on various structured prediction problems reveals to be versatile and able to handle large datasets.

Dates and versions

hal-03282445 , version 1 (09-07-2021)

Identifiers

Cite

Luc Brogat-Motte, Alessandro Rudi, Celine Brouard, Juho Rousu, Florence d'Alché-Buc. Learning Output Embeddings in Structured Prediction. 2021. ⟨hal-03282445⟩
67 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More