# Liquid Democracy for Low-Cost Ensemble Pruning

arXiv: https://arxiv.org/abs/2401.17443 · HTML: https://mlsanity.com/paper/2401.17443/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 7 of 7)

- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)
- [On Rational Delegations in Liquid Democracy](https://mlsanity.com/paper/1802.08020/) (2018)
- [Binary Voting with Delegable Proxy: An Analysis of Liquid Democracy](https://mlsanity.com/paper/1707.08741/) (2017)
- [Voting with Random Classifiers (VORACE): Theoretical and Experimental Analysis](https://mlsanity.com/paper/1909.08996/) (2019)
- [When Can Liquid Democracy Unveil the Truth?](https://mlsanity.com/paper/2104.01828/) (2021)

## Abstract (arXiv)

We argue that there is a strong connection between ensemble learning and a delegative voting paradigm -- liquid democracy -- that can be leveraged to reduce ensemble training costs. We present an incremental training procedure that identifies and removes redundant classifiers from an ensemble via delegation mechanisms inspired by liquid democracy. Through both analysis and extensive experiments we show that this process greatly reduces the computational cost of training compared to training a full ensemble. By carefully selecting the underlying delegation mechanism, weight centralization in the classifier population is avoided, leading to higher accuracy than some boosting methods. Furthermore, this work serves as an exemplar of how frameworks from computational social choice literature can be applied to problems in nontraditional domains.