Adapting Tensor Kernel Machines to Enable Efficient Transfer Learning for Seizure Detection

TL;DR

This paper introduces an efficient transfer learning method using tensor kernel machines for seizure detection in EEG data, enabling personalized models with fewer parameters and faster inference suitable for wearable devices.

Contribution

It presents the adaptive tensor kernel machine (Adapt-TKM), a novel approach that leverages low-rank tensor networks for efficient transfer learning in seizure detection.

Findings

Achieves better seizure detection performance with minimal patient-specific data.

Uses 100 times fewer parameters than adaptive SVM, enabling faster inference.

Demonstrates effectiveness on behind-the-ear EEG data.

Abstract

Transfer learning aims to optimize performance in a target task by learning from a related source problem. In this work, we propose an efficient transfer learning method using a tensor kernel machine. Our method takes inspiration from the adaptive SVM and hence transfers 'knowledge' from the source to the 'adapted' model via regularization. The main advantage of using tensor kernel machines is that they leverage low-rank tensor networks to learn a compact non-linear model in the primal domain. This allows for a more efficient adaptation without adding more parameters to the model. To demonstrate the effectiveness of our approach, we apply the adaptive tensor kernel machine (Adapt-TKM) to seizure detection on behind-the-ear EEG. By personalizing patient-independent models with a small amount of patient-specific data, the patient-adapted model (which utilizes the Adapt-TKM), achieves better performance compared to the patient-independent and fully patient-specific models. Notably, it is able to do so while requiring around 100 times fewer parameters than the adaptive SVM model, leading to a correspondingly faster inference speed. This makes the Adapt-TKM especially useful for resource-constrained wearable devices.