A Deep Learning Model for Structured Outputs with High-order Interaction
This addresses structured output regression, a less explored area in machine learning, with potential extensions to classification.
The paper tackles the problem of modeling structured outputs with high-order interactions, proposing a deep learning model that integrates high-order hidden units, guided discriminative pretraining, and high-order auto-encoders, achieving state-of-the-art performances on three datasets.
Many real-world applications are associated with structured data, where not only input but also output has interplay. However, typical classification and regression models often lack the ability of simultaneously exploring high-order interaction within input and that within output. In this paper, we present a deep learning model aiming to generate a powerful nonlinear functional mapping from structured input to structured output. More specifically, we propose to integrate high-order hidden units, guided discriminative pretraining, and high-order auto-encoders for this purpose. We evaluate the model with three datasets, and obtain state-of-the-art performances among competitive methods. Our current work focuses on structured output regression, which is a less explored area, although the model can be extended to handle structured label classification.