Domain Independent SVM for Transfer Learning in Brain Decoding

TL;DR

This paper introduces DI-SVM, a transfer learning method for brain decoding that minimizes domain dependence using HSIC, leading to improved accuracy across various transfer tasks with limited data.

Contribution

The paper proposes a novel domain-independent SVM approach that effectively reduces domain discrepancies in brain imaging transfer learning.

Findings

DI-SVM outperforms eight competing methods.

Achieves over 24% improvement on multi-source tasks.

Demonstrates effectiveness on 13 transfer learning tasks.

Abstract

Brain imaging data are important in brain sciences yet expensive to obtain, with big volume (i.e., large p) but small sample size (i.e., small n). To tackle this problem, transfer learning is a promising direction that leverages source data to improve performance on related, target data. Most transfer learning methods focus on minimizing data distribution mismatch. However, a big challenge in brain imaging is the large domain discrepancies in cognitive experiment designs and subject-specific structures and functions. A recent transfer learning approach minimizes domain dependence to learn common features across domains, via the Hilbert-Schmidt Independence Criterion (HSIC). Inspired by this method, we propose a new Domain Independent Support Vector Machine (DI-SVM) for transfer learning in brain condition decoding. Specifically, DI-SVM simultaneously minimizes the SVM empirical risk and the dependence on domain information via a simplified HSIC. We use public data to construct 13 transfer learning tasks in brain decoding, including three interesting multi-source transfer tasks. Experiments show that DI-SVM's superior performance over eight competing methods on these tasks, particularly an improvement of more than 24% on multi-source transfer tasks.