# Deep Extreme Multi-label Learning

arXiv: https://arxiv.org/abs/1704.03718 · HTML: https://mlsanity.com/paper/1704.03718/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2017.

## Built on by (most cited first, 24 of 24)

- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [NGAME: Negative Mining-aware Mini-batching for Extreme Classification](https://mlsanity.com/paper/2207.04452/) (2022)
- [Does Head Label Help for Long-Tailed Multi-Label Text Classification](https://mlsanity.com/paper/2101.09704/) (2021)
- [A Survey on Extreme Multi-label Learning](https://mlsanity.com/paper/2210.03968/) (2022)
- [Dual-Encoders for Extreme Multi-Label Classification](https://mlsanity.com/paper/2310.10636/) (2023)
- [Multi-label Ranking: Mining Multi-label and Label Ranking Data](https://mlsanity.com/paper/2101.00583/) (2021)
- [LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification](https://mlsanity.com/paper/2103.14620/) (2021)
- [Multi-target prediction for dummies using two-branch neural networks](https://mlsanity.com/paper/2104.09967/) (2021)
- [Improving Predictions of Tail-end Labels using Concatenated BioMed-Transformers for Long Medical Documents](https://mlsanity.com/paper/2112.01718/) (2021)
- [Rank4Class: A Ranking Formulation for Multiclass Classification](https://mlsanity.com/paper/2112.09727/) (2021)
- [Efficient Image Representation Learning with Federated Sampled Softmax](https://mlsanity.com/paper/2203.04888/) (2022)
- [Light-weight Deep Extreme Multilabel Classification](https://mlsanity.com/paper/2304.11045/) (2023)
- [Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy](https://mlsanity.com/paper/2405.04759/) (2024)
- [On Riemannian Approach for Constrained Optimization Model in Extreme Classification Problems](https://mlsanity.com/paper/2109.15021/) (2021)
- [GUDN: A novel guide network with label reinforcement strategy for extreme multi-label text classification](https://mlsanity.com/paper/2201.11582/) (2022)
- [Label Dependencies-aware Set Prediction Networks for Multi-label Text Classification](https://mlsanity.com/paper/2304.07022/) (2023)
- [Graph Regularized Encoder Training for Extreme Classification](https://mlsanity.com/paper/2402.18434/) (2024)
- [Multi-label Learning with Random Circular Vectors](https://mlsanity.com/paper/2407.05656/) (2024)
- [Priberam at MESINESP Multi-label Classification of Medical Texts Task](https://mlsanity.com/paper/2105.05614/) (2021)
- [Research on Domain Information Mining and Theme Evolution of Scientific Papers](https://mlsanity.com/paper/2204.08476/) (2022)
- [Pairwise Instance Relation Augmentation for Long-tailed Multi-label Text Classification](https://mlsanity.com/paper/2211.10685/) (2022)
- [Minimal Learning Machine for Multi-Label Learning](https://mlsanity.com/paper/2305.05518/) (2023)
- [Scalable Label Distribution Learning for Multi-Label Classification](https://mlsanity.com/paper/2311.16556/) (2023)
- [Semi-Supervised Learning with Balanced Deep Representation Distributions](https://mlsanity.com/paper/2603.21056/) (2026)

## Abstract (arXiv)

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves 2L possible label sets especially when the label dimension L is huge, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by originally establishing an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems including multi-label classification, however it has not been properly introduced to XML, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Extensive experiments on public datasets for XML show that our method performs competitive against state-of-the-art result.