# Learning Deep Latent Spaces for Multi-Label Classification

arXiv: https://arxiv.org/abs/1707.00418 · HTML: https://mlsanity.com/paper/1707.00418/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2017.

## Built on by (most cited first, 21 of 21)

- [SpanEmo: Casting Multi-label Emotion Classification as Span-prediction](https://mlsanity.com/paper/2101.10038/) (2021)
- [Modeling Multi-Label Action Dependencies for Temporal Action Localization](https://mlsanity.com/paper/2103.03027/) (2021)
- [Deep Learning for Multi-Label Learning: A Comprehensive Survey](https://mlsanity.com/paper/2401.16549/) (2024)
- [HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders](https://mlsanity.com/paper/2103.06375/) (2021)
- [A Survey on Extreme Multi-label Learning](https://mlsanity.com/paper/2210.03968/) (2022)
- [Spatial-context-aware deep neural network for multi-class image classification](https://mlsanity.com/paper/2111.12296/) (2021)
- [From Multi-label Learning to Cross-Domain Transfer: A Model-Agnostic Approach](https://mlsanity.com/paper/2207.11742/) (2022)
- [Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond](https://mlsanity.com/paper/2208.14439/) (2022)
- [Leveraging VAE-Derived Latent Spaces for Enhanced Malware Detection with Machine Learning Classifiers](https://mlsanity.com/paper/2503.20803/) (2025)
- [Multi-target prediction for dummies using two-branch neural networks](https://mlsanity.com/paper/2104.09967/) (2021)
- [SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifier](https://mlsanity.com/paper/2206.13923/) (2022)
- [Out of Distribution Reasoning by Weakly-Supervised Disentangled Logic Variational Autoencoder](https://mlsanity.com/paper/2210.09959/) (2022)
- [GUDN: A novel guide network with label reinforcement strategy for extreme multi-label text classification](https://mlsanity.com/paper/2201.11582/) (2022)
- [DeepHelp: Deep Learning for Shout Crisis Text Conversations](https://mlsanity.com/paper/2110.13244/) (2021)
- [Calorie Aware Automatic Meal Kit Generation from an Image](https://mlsanity.com/paper/2112.09839/) (2021)
- [Towards Micro-video Thumbnail Selection via a Multi-label Visual-semantic Embedding Model](https://mlsanity.com/paper/2202.02930/) (2022)
- [Research on Domain Information Mining and Theme Evolution of Scientific Papers](https://mlsanity.com/paper/2204.08476/) (2022)
- [Interval Type-2 Fuzzy Neural Networks for Multi-Label Classification](https://mlsanity.com/paper/2302.10430/) (2023)
- [Multi-Label Takagi-Sugeno-Kang Fuzzy System](https://mlsanity.com/paper/2309.11469/) (2023)
- [A Consistent Lebesgue Measure for Multi-label Learning](https://mlsanity.com/paper/2402.00324/) (2024)
- [Learned Cross-Task Relationships in Multi-Task Models](https://mlsanity.com/paper/2609.28776/) (2026)

## Abstract (arXiv)

Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance. We propose a novel deep neural networks (DNN) based model, Canonical Correlated AutoEncoder (C2AE), for solving this task. Aiming at better relating feature and label domain data for improved classification, we uniquely perform joint feature and label embedding by deriving a deep latent space, followed by the introduction of label-correlation sensitive loss function for recovering the predicted label outputs. Our C2AE is achieved by integrating the DNN architectures of canonical correlation analysis and autoencoder, which allows end-to-end learning and prediction with the ability to exploit label dependency. Moreover, our C2AE can be easily extended to address the learning problem with missing labels. Our experiments on multiple datasets with different scales confirm the effectiveness and robustness of our proposed method, which is shown to perform favorably against state-of-the-art methods for multi-label classification.