Deep Learning with a Rethinking Structure for Multi-label Classification
This work addresses multi-label classification problems, which are important for applications like image tagging, by offering a flexible method that adapts to various evaluation needs, though it appears incremental as it builds on existing deep learning techniques.
The paper tackles multi-label classification by proposing a deep learning framework with a rethinking structure that uses memory in recurrent neural networks to extract hidden label correlations, leading to improved performance across different evaluation criteria and superior results over state-of-the-art algorithms.
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.