Rank4Class: A Ranking Formulation for Multiclass Classification

Abstract

Multiclass classification (MCC) is a fundamental machine learning problem which aims to classify each instance into one of a predefined set of classes. Given an instance, a classification model computes a score for each class, all of which are then used to sort the classes. The performance of a classification model is usually measured by Top-K Accuracy/Error (e.g., K = 1 or 5). In this paper, we do not aim to propose new neural representation learning models as most recent works do, but to show that it is easy to boost MCC performance with a novel formulation through the lens of ranking. In particular, by viewing MCC as to rank classes for an instance, we first argue that ranking metrics, such as Normalized Discounted Cumulative Gain (NDCG), can be more informative than existing Top-K metrics. We further demonstrate that the dominant neural MCC architecture can be formulated as a neural ranking framework with a specific set of design choices. Based on such generalization, we show that it is straightforward and intuitive to leverage techniques from the rich information retrieval literature to improve the MCC performance out of the box. Extensive empirical results on both text and image classification tasks with diverse datasets and backbone models (e.g., BERT and ResNet for text and image classification) show the value of our proposed framework.

Rank-based deep learning from citizen-science data to model plant communities

“…Although less common in ecology, many problems in data science require minimizing ranks, and various cost functions have been developed to address this problem 26 . Some of them, in particular the Normalized Discounted Cumulative Gain 27 (NDCG), can readily be employed in multispecies DNNs 28 .…”

Multispecies deep learning using citizen science data produces more informative plant community models

“…Although less common in ecology, many problems in data science require minimizing ranks, and various cost functions have been developed to address this problem 31 . Some of them, in particular the Normalized Discounted Cumulative Gain 32 (NDCG), can readily be employed in multispecies DNNs 33 .…”