Learning Output Embeddings in Structured Prediction

TL;DR

This paper introduces a method to jointly learn output embeddings and regression functions for structured prediction, leveraging prior output information and unsupervised data to improve efficiency and accuracy.

Contribution

It proposes a novel joint learning framework for output embeddings and regression in structured prediction, with theoretical guarantees and reduced computational complexity.

Findings

Proven consistency and excess risk bounds for the new predictor.

Empirical results show versatility and scalability to large datasets.

Reduced computational complexity compared to previous output kernel methods.

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.