# Collaboration based Multi-Label Learning

arXiv: https://arxiv.org/abs/1902.03047 · HTML: https://mlsanity.com/paper/1902.03047/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2019.

## Built on by (most cited first, 11 of 11)

- [Multi-Label Classification Neural Networks with Hard Logical Constraints](https://mlsanity.com/paper/2103.13427/) (2021)
- [Tailor Versatile Multi-modal Learning for Multi-label Emotion Recognition](https://mlsanity.com/paper/2201.05834/) (2022)
- [Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention](https://mlsanity.com/paper/2203.03483/) (2022)
- [Multi-label Classification with High-rank and High-order Label Correlations](https://mlsanity.com/paper/2207.04197/) (2022)
- [GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2309.00923/) (2023)
- [Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2408.12253/) (2024)
- [Analysis and Detection against Network Attacks in the Overlapping Phenomenon of Behavior Attribute](https://mlsanity.com/paper/2310.10660/) (2023)
- [Research on Domain Information Mining and Theme Evolution of Scientific Papers](https://mlsanity.com/paper/2204.08476/) (2022)
- [Towards Effective Multi-Label Recognition Attacks via Knowledge Graph Consistency](https://mlsanity.com/paper/2207.05137/) (2022)
- [Implicit Regularization for Multi-label Feature Selection](https://mlsanity.com/paper/2411.11436/) (2024)
- [A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition](https://mlsanity.com/paper/2609.06579/) (2026)

## Abstract (arXiv)

It is well-known that exploiting label correlations is crucially important to multi-label learning. Most of the existing approaches take label correlations as prior knowledge, which may not correctly characterize the real relationships among labels. Besides, label correlations are normally used to regularize the hypothesis space, while the final predictions are not explicitly correlated. In this paper, we suggest that for each individual label, the final prediction involves the collaboration between its own prediction and the predictions of other labels. Based on this assumption, we first propose a novel method to learn the label correlations via sparse reconstruction in the label space. Then, by seamlessly integrating the learned label correlations into model training, we propose a novel multi-label learning approach that aims to explicitly account for the correlated predictions of labels while training the desired model simultaneously. Extensive experimental results show that our approach outperforms the state-of-the-art counterparts.