# RLSEP: Learning Label Ranks for Multi-label Classification

arXiv: https://arxiv.org/abs/2212.04022 · HTML: https://mlsanity.com/paper/2212.04022/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 8 Dec 2022.

## Builds on (most cited first, 11 of 11)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank](https://mlsanity.com/paper/1902.06285/) (2019)
- [Deep Convolutional Ranking for Multilabel Image Annotation](https://mlsanity.com/paper/1312.4894/) (2013)
- [Improving Pairwise Ranking for Multi-label Image Classification](https://mlsanity.com/paper/1704.03135/) (2017)
- [Learning Single-Image Depth from Videos using Quality Assessment Networks](https://mlsanity.com/paper/1806.09573/) (2018)
- [A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation](https://mlsanity.com/paper/2010.07091/) (2020)
- [Relative Depth Estimation as a Ranking Problem](https://mlsanity.com/paper/2010.06944/) (2020)
- [Detecting Visual Design Principles in Art and Architecture through Deep Convolutional Neural Networks](https://mlsanity.com/paper/2108.04048/) (2021)
- [Multi-label Ranking: Mining Multi-label and Label Ranking Data](https://mlsanity.com/paper/2101.00583/) (2021)

## Abstract (arXiv)

Multi-label ranking maps instances to a ranked set of predicted labels from multiple possible classes. The ranking approach for multi-label learning problems received attention for its success in multi-label classification, with one of the well-known approaches being pairwise label ranking. However, most existing methods assume that only partial information about the preference relation is known, which is inferred from the partition of labels into a positive and negative set, then treat labels with equal importance. In this paper, we focus on the unique challenge of ranking when the order of the true label set is provided. We propose a novel dedicated loss function to optimize models by incorporating penalties for incorrectly ranked pairs, and make use of the ranking information present in the input. Our method achieves the best reported performance measures on both synthetic and real world ranked datasets and shows improvements on overall ranking of labels. Our experimental results demonstrate that our approach is generalizable to a variety of multi-label classification and ranking tasks, while revealing a calibration towards a certain ranking ordering.