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.

References in corpus (11)

• A Consistent Regularization Approach for Structured Prediction
• On the Sample Complexity of Subspace Learning
• A Generalized Kernel Approach to Structured Output Learning
• Structured Prediction Energy Networks
• A Structured Prediction Approach for Label Ranking
• Autoencoding any Data through Kernel Autoencoders
• A General Theory for Structured Prediction with Smooth Convex Surrogates
• A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings
• Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction
• Quantifying Learning Guarantees for Convex but Inconsistent Surrogates
• Duality in RKHSs with Infinite Dimensional Outputs: Application to Robust Losses