# Uncertainty in Multitask Transfer Learning

arXiv: https://arxiv.org/abs/1806.07528 · HTML: https://mlsanity.com/paper/1806.07528/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [Evaluation Gaps in Machine Learning Practice](https://mlsanity.com/paper/2205.05256/) (2022)
- [From partners to populations: A hierarchical Bayesian account of coordination and convention](https://mlsanity.com/paper/2104.05857/) (2021)
- [The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning](https://mlsanity.com/paper/2111.05326/) (2021)
- [The Effect of Diversity in Meta-Learning](https://mlsanity.com/paper/2201.11775/) (2022)
- [Towards Task Sampler Learning for Meta-Learning](https://mlsanity.com/paper/2307.08924/) (2023)
- [Rethinking Meta-Learning from a Learning Lens](https://mlsanity.com/paper/2409.08474/) (2024)
- [Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching](https://mlsanity.com/paper/2412.18703/) (2024)

## Abstract (arXiv)

Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The posterior can go beyond the mean field approximation and yields good uncertainty on the performed experiments. Analysis on toy tasks shows that it can learn from significantly different tasks while finding similarities among them. Experiments of Mini-Imagenet yields the new state of the art with 74.5% accuracy on 5 shot learning. Finally, we provide experiments showing that other existing methods can fail to perform well in different benchmarks.