Quantification using Permutation-Invariant Networks based on Histograms
This addresses quantification tasks for scenarios where only bag-level prevalence labels are available, offering a more flexible and efficient approach, though it is incremental in improving existing deep learning methods for set processing.
The paper tackles the problem of class prevalence estimation (quantification) by proposing HistNetQ, a deep neural network architecture that uses permutation-invariant histogram representations, which outperforms state-of-the-art methods in experiments from a quantification competition.
Quantification, also known as class prevalence estimation, is the supervised learning task in which a model is trained to predict the prevalence of each class in a given bag of examples. This paper investigates the application of deep neural networks to tasks of quantification in scenarios where it is possible to apply a symmetric supervised approach that eliminates the need for classification as an intermediary step, directly addressing the quantification problem. Additionally, it discusses existing permutation-invariant layers designed for set processing and assesses their suitability for quantification. In light of our analysis, we propose HistNetQ, a novel neural architecture that relies on a permutation-invariant representation based on histograms that is specially suited for quantification problems. Our experiments carried out in the only quantification competition held to date, show that HistNetQ outperforms other deep neural architectures devised for set processing, as well as the state-of-the-art quantification methods. Furthermore, HistNetQ offers two significant advantages over traditional quantification methods: i) it does not require the labels of the training examples but only the prevalence values of a collection of training bags, making it applicable to new scenarios; and ii) it is able to optimize any custom quantification-oriented loss function.