# Theoretical Foundation of Co-Training and Disagreement-Based Algorithms

arXiv: https://arxiv.org/abs/1708.04403 · HTML: https://mlsanity.com/paper/1708.04403/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2017.

## Built on by (most cited first, 6 of 6)

- [Quantifying the Gain in Weak-to-Strong Generalization](https://mlsanity.com/paper/2405.15116/) (2024)
- [Semi-Supervised Learning with Multi-Head Co-Training](https://mlsanity.com/paper/2107.04795/) (2021)
- [Estimating Soft Labels for Out-of-Domain Intent Detection](https://mlsanity.com/paper/2211.05561/) (2022)
- [Agreement or Disagreement in Noise-tolerant Mutual Learning?](https://mlsanity.com/paper/2203.15317/) (2022)
- [SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks](https://mlsanity.com/paper/2509.22581/) (2025)
- [Human-Corrected Labels Learning: Enhancing Labels Quality via Human Correction of VLMs Discrepancies](https://mlsanity.com/paper/2511.09063/) (2025)

## Abstract (arXiv)

Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers separately on two sufficient and redundant views; while for the applications where there is only one view, several successful variants of co-training with two different classifiers on single-view data instead of two views have been proposed. For these disagreement-based approaches, there are several important issues which still are unsolved, in this article we present theoretical analyses to address these issues, which provides a theoretical foundation of co-training and disagreement-based approaches.