# Across-subject ensemble-learning alleviates the need for large samples for fMRI decoding

arXiv: https://arxiv.org/abs/2407.12056 · HTML: https://mlsanity.com/paper/2407.12056/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 5 of 5)

- [Machine Learning for Neuroimaging with Scikit-Learn](https://mlsanity.com/paper/1412.3919/) (2014)
- [BOLD5000: A public fMRI dataset of 5000 images](https://mlsanity.com/paper/1809.01281/) (2018)
- [Fine-grain atlases of functional modes for fMRI analysis](https://mlsanity.com/paper/2003.05405/) (2020)
- [Aligning individual brains with Fused Unbalanced Gromov-Wasserstein](https://mlsanity.com/paper/2206.09398/) (2022)
- [Personalized visual encoding model construction with small data](https://mlsanity.com/paper/2202.02245/) (2022)

## Built on by (most cited first, 3 of 3)

- [Optimizing fMRI Data Acquisition for Decoding Natural Speech with Limited Participants](https://mlsanity.com/paper/2505.21304/) (2025)
- [Hi-DREAM: Brain-Inspired Hierarchical Diffusion for fMRI-to-Image Reconstruction via ROI Encoder and VisuAl Mapping](https://mlsanity.com/paper/2511.11437/) (2025)
- [DD-INR: Dynamics-Driven Implicit Neural Representation for Accelerated Whole-Brain Functional MRI Reconstruction](https://mlsanity.com/paper/2606.10756/) (2026)

## Abstract (arXiv)

Decoding cognitive states from functional magnetic resonance imaging is central to understanding the functional organization of the brain. Within-subject decoding avoids between-subject correspondence problems but requires large sample sizes to make accurate predictions; obtaining such large sample sizes is both challenging and expensive. Here, we investigate an ensemble approach to decoding that combines the classifiers trained on data from other subjects to decode cognitive states in a new subject. We compare it with the conventional decoding approach on five different datasets and cognitive tasks. We find that it outperforms the conventional approach by up to 20% in accuracy, especially for datasets with limited per-subject data. The ensemble approach is particularly advantageous when the classifier is trained in voxel space. Furthermore, a Multi-layer Perceptron turns out to be a good default choice as an ensemble method. These results show that the pre-training strategy reduces the need for large per-subject data.