# SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels

arXiv: https://arxiv.org/abs/1805.09622 · HTML: https://mlsanity.com/paper/1805.09622/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2018.

## Built on by (most cited first, 5 of 5)

- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels](https://mlsanity.com/paper/2103.13646/) (2021)
- [HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks](https://mlsanity.com/paper/2102.02515/) (2021)
- [Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization](https://mlsanity.com/paper/2505.00812/) (2025)
- [Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling](https://mlsanity.com/paper/2208.10683/) (2022)

## Abstract (arXiv)

We present SOSELETO (SOurce SELEction for Target Optimization), a new method for exploiting a source dataset to solve a classification problem on a target dataset. SOSELETO is based on the following simple intuition: some source examples are more informative than others for the target problem. To capture this intuition, source samples are each given weights; these weights are solved for jointly with the source and target classification problems via a bilevel optimization scheme. The target therefore gets to choose the source samples which are most informative for its own classification task. Furthermore, the bilevel nature of the optimization acts as a kind of regularization on the target, mitigating overfitting. SOSELETO may be applied to both classic transfer learning, as well as the problem of training on datasets with noisy labels; we show state of the art results on both of these problems.