# Co-training for Demographic Classification Using Deep Learning from Label Proportions

arXiv: https://arxiv.org/abs/1709.04108 · HTML: https://mlsanity.com/paper/1709.04108/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2017.

## Built on by (most cited first, 28 of 28)

- [Learning from Label Proportions by Learning with Label Noise](https://mlsanity.com/paper/2203.02496/) (2022)
- [Easy Learning from Label Proportions](https://mlsanity.com/paper/2302.03115/) (2023)
- [Two-stage Training for Learning from Label Proportions](https://mlsanity.com/paper/2105.10635/) (2021)
- [Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization](https://mlsanity.com/paper/2302.08947/) (2023)
- [A Unified Approach to Count-Based Weakly-Supervised Learning](https://mlsanity.com/paper/2311.13718/) (2023)
- [MixBag: Bag-Level Data Augmentation for Learning from Label Proportions](https://mlsanity.com/paper/2308.08822/) (2023)
- [Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation](https://mlsanity.com/paper/2310.08056/) (2023)
- [Learning from Partial Label Proportions for Whole Slide Image Segmentation](https://mlsanity.com/paper/2405.09041/) (2024)
- [Fast learning from label proportions with small bags](https://mlsanity.com/paper/2110.03426/) (2021)
- [LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportions](https://mlsanity.com/paper/2310.10096/) (2023)
- [Proportion Estimation by Masked Learning from Label Proportion](https://mlsanity.com/paper/2405.04815/) (2024)
- [Training image classifiers using Semi-Weak Label Data](https://mlsanity.com/paper/2103.10608/) (2021)
- [Learning from Label Proportions with Instance-wise Consistency](https://mlsanity.com/paper/2203.12836/) (2022)
- [Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions](https://mlsanity.com/paper/2401.11081/) (2024)
- [Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags](https://mlsanity.com/paper/2408.14130/) (2024)
- [Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions](https://mlsanity.com/paper/2411.10364/) (2024)
- [Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labeling](https://mlsanity.com/paper/2506.22301/) (2025)
- [Learning under Label Proportions for Text Classification](https://mlsanity.com/paper/2310.11707/) (2023)
- [Evaluating LLP Methods: Challenges and Approaches](https://mlsanity.com/paper/2310.19065/) (2023)
- [FRACTAL: Fine-Grained Scoring from Aggregate Text Labels](https://mlsanity.com/paper/2404.04817/) (2024)
- [Class-aware and Augmentation-free Contrastive Learning from Label Proportion](https://mlsanity.com/paper/2408.06743/) (2024)
- [Learning from Label Proportions and Covariate-shifted Instances](https://mlsanity.com/paper/2411.12334/) (2024)
- [Aggregating Data for Optimal and Private Learning](https://mlsanity.com/paper/2411.19045/) (2024)
- [Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions](https://mlsanity.com/paper/2505.23031/) (2025)
- [Leveraging Label Proportion Prior for Class-Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2603.02957/) (2026)
- [Learning from Label Proportions with Dual-proportion Constraints](https://mlsanity.com/paper/2603.21153/) (2026)
- [Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions](https://mlsanity.com/paper/2604.24347/) (2026)
- [Multi-Label Proportion Learning for Sea-Ice Type Prediction](https://mlsanity.com/paper/2609.16347/) (2026)

## Abstract (arXiv)

Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we introduce a deep neural network for the Learning from Label Proportion (LLP) setting, in which the training data consist of bags of unlabeled instances with associated label distributions for each bag. We introduce a new regularization layer, Batch Averager, that can be appended to the last layer of any deep neural network to convert it from supervised learning to LLP. This layer can be implemented readily with existing deep learning packages. To further support domains in which the data consist of two conditionally independent feature views (e.g. image and text), we propose a co-training algorithm that iteratively generates pseudo bags and refits the deep LLP model to improve classification accuracy. We demonstrate our models on demographic attribute classification (gender and race/ethnicity), which has many applications in social media analysis, public health, and marketing. We conduct experiments to predict demographics of Twitter users based on their tweets and profile image, without requiring any user-level annotations for training. We find that the deep LLP approach outperforms baselines for both text and image features separately. Additionally, we find that co-training algorithm improves image and text classification by 4% and 8% absolute F1, respectively. Finally, an ensemble of text and image classifiers further improves the absolute F1 measure by 4% on average.