Deep Learning with a Rethinking Structure for Multi-label Classification

TL;DR

This paper introduces a novel deep learning framework with a rethinking structure that leverages memory in recurrent neural networks to better capture label correlations in multi-label classification, adaptable to various evaluation criteria.

Contribution

The proposed framework uniquely incorporates a memory-based rethinking process within deep learning to improve multi-label classification performance and flexibility.

Findings

Improves multi-label classification accuracy across multiple datasets.

Effectively adapts to different evaluation criteria.

Outperforms state-of-the-art algorithms in experiments.

Abstract

Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect the learning algorithm to take the hidden correlation of the labels into account to improve the prediction performance. Extracting the hidden correlation is generally a challenging task. In this work, we propose a novel deep learning framework to better extract the hidden correlation with the help of the memory structure within recurrent neural networks. The memory stores the temporary guesses on the labels and effectively allows the framework to rethink about the goodness and correlation of the guesses before making the final prediction. Furthermore, the rethinking process makes it easy to adapt to different evaluation criteria to match real-world application needs. In particular, the framework can be trained in an end-to-end style with respect to any given MLC evaluation criteria. The end-to-end design can be seamlessly combined with other deep learning techniques to conquer challenging MLC problems like image tagging. Experimental results across many real-world data sets justify that the rethinking framework indeed improves MLC performance across different evaluation criteria and leads to superior performance over state-of-the-art MLC algorithms.