# A Deep Learning Approach to Unsupervised Ensemble Learning

arXiv: https://arxiv.org/abs/1602.02285 · HTML: https://mlsanity.com/paper/1602.02285/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2016.

## Built on by (most cited first, 12 of 12)

- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects](https://mlsanity.com/paper/2101.06116/) (2021)
- [A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models](https://mlsanity.com/paper/2404.14955/) (2024)
- [FUSE: Ensembling Verifiers with Zero Labeled Data](https://mlsanity.com/paper/2604.18547/) (2026)
- [A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines](https://mlsanity.com/paper/2111.07379/) (2021)
- [Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning](https://mlsanity.com/paper/2210.05320/) (2022)
- [Sharp bounds on aggregate expert error](https://mlsanity.com/paper/2407.16642/) (2024)
- [Dependence-Aware Label Aggregation for LLM-as-a-Judge via Ising Models](https://mlsanity.com/paper/2601.22336/) (2026)
- [Deep Negative Correlation Classification](https://mlsanity.com/paper/2212.07070/) (2022)
- [Scheduling to Learn In An Unsupervised Online Streaming Model](https://mlsanity.com/paper/2112.01576/) (2021)
- [Ranking and Combining Latent Structured Predictive Scores without Labeled Data](https://mlsanity.com/paper/2408.07796/) (2024)
- [Unsupervised Ensemble Learning Through Deep Energy-based Models](https://mlsanity.com/paper/2601.20556/) (2026)

## Abstract (arXiv)

We show how deep learning methods can be applied in the context of crowdsourcing and unsupervised ensemble learning. First, we prove that the popular model of Dawid and Skene, which assumes that all classifiers are conditionally independent, is em equivalent to a Restricted Boltzmann Machine (RBM) with a single hidden node. Hence, under this model, the posterior probabilities of the true labels can be instead estimated via a trained RBM. Next, to address the more general case, where classifiers may strongly violate the conditional independence assumption, we propose to apply RBM-based Deep Neural Net (DNN). Experimental results on various simulated and real-world datasets demonstrate that our proposed DNN approach outperforms other state-of-the-art methods, in particular when the data violates the conditional independence assumption.