A Deep Learning Model for Structured Outputs with High-order Interaction

TL;DR

This paper introduces a deep learning model designed to handle structured input and output data by capturing high-order interactions, achieving state-of-the-art results in structured output regression tasks.

Contribution

The paper proposes a novel deep learning architecture that integrates high-order hidden units, discriminative pretraining, and auto-encoders to model complex structured data interactions.

Findings

Achieved state-of-the-art performance on three datasets.

Effectively models high-order interactions in structured data.

Extensible to structured label classification tasks.

Abstract

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.