2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets

TL;DR

This paper presents the BEETL competition, which advances transfer learning methods for EEG data, addressing challenges like subject variability and heterogeneity, and establishes new benchmarks for medical diagnostics and BCI tasks.

Contribution

It introduces two transfer learning challenges for EEG data, fostering progress in subject-independent analysis and setting new state-of-the-art results.

Findings

Over 30 teams participated, demonstrating the potential of deep transfer learning.

The competition achieved new state-of-the-art performance on the BEETL benchmark.

Combining set theory with machine learning improved EEG analysis.

Abstract

Transfer learning and meta-learning offer some of the most promising avenues to unlock the scalability of healthcare and consumer technologies driven by biosignal data. This is because current methods cannot generalise well across human subjects' data and handle learning from different heterogeneously collected data sets, thus limiting the scale of training data. On the other side, developments in transfer learning would benefit significantly from a real-world benchmark with immediate practical application. Therefore, we pick electroencephalography (EEG) as an exemplar for what makes biosignal machine learning hard. We design two transfer learning challenges around diagnostics and Brain-Computer-Interfacing (BCI), that have to be solved in the face of low signal-to-noise ratios, major variability among subjects, differences in the data recording sessions and techniques, and even between the specific BCI tasks recorded in the dataset. Task 1 is centred on the field of medical diagnostics, addressing automatic sleep stage annotation across subjects. Task 2 is centred on Brain-Computer Interfacing (BCI), addressing motor imagery decoding across both subjects and data sets. The BEETL competition with its over 30 competing teams and its 3 winning entries brought attention to the potential of deep transfer learning and combinations of set theory and conventional machine learning techniques to overcome the challenges. The results set a new state-of-the-art for the real-world BEETL benchmark.