Enhance and Reuse: A Dual-Mechanism Approach to Boost Deep Forest for Label Distribution Learning

TL;DR

This paper introduces ERDF, a dual-mechanism deep forest approach that leverages label correlations and feature reuse to improve label distribution learning performance.

Contribution

The paper proposes ERDF, a novel deep forest method that enhances features using label correlation and reuses features to stabilize training in LDL tasks.

Findings

ERDF outperforms existing methods on six metrics.

Feature enhancement improves label correlation utilization.

Feature reuse stabilizes training and prevents noise propagation.

Abstract

Label distribution learning (LDL) requires the learner to predict the degree of correlation between each sample and each label. To achieve this, a crucial task during learning is to leverage the correlation among labels. Deep Forest (DF) is a deep learning framework based on tree ensembles, whose training phase does not rely on backpropagation. DF performs in-model feature transform using the prediction of each layer and achieves competitive performance on many tasks. However, its exploration in the field of LDL is still in its infancy. The few existing methods that apply DF to the field of LDL do not have effective ways to utilize the correlation among labels. Therefore, we propose a method named Enhanced and Reused Feature Deep Forest (ERDF). It mainly contains two mechanisms: feature enhancement exploiting label correlation and measure-aware feature reuse. The first one is to utilize the correlation among labels to enhance the original features, enabling the samples to acquire more comprehensive information for the task of LDL. The second one performs a reuse operation on the features of samples that perform worse than the previous layer on the validation set, in order to ensure the stability of the training process. This kind of Enhance-Reuse pattern not only enables samples to enrich their features but also validates the effectiveness of their new features and conducts a reuse process to prevent the noise from spreading further. Experiments show that our method outperforms other comparison algorithms on six evaluation metrics.