EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding

2025-06-23

AI Summary

This study addresses the poor generalizability of EEG decoding models by tackling two key challenges: (1) zero-shot cross-task and cross-subject decoding, and (2) predicting psychopathology-related metrics from EEG. To this end, we introduce the first large-scale, multi-task, multi-subject, high-density (128-channel) EEG dataset, and propose a joint modeling framework integrating deep neural networks with demographic constraints to support zero-shot transfer and continuous psychological trait regression. Our contributions include: (1) releasing an open-source benchmark dataset and tunable baseline models; (2) the first systematic empirical validation of zero-shot EEG decoding feasibility on unseen tasks and subjects; and (3) identifying cross-individually stable EEG features significantly associated with depression, anxiety, and other psychological dimensions—yielding interpretable, biologically grounded biomarkers for computational psychiatry.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Current electroencephalogram (EEG) decoding models are typically trained on small numbers of subjects performing a single task. Here, we introduce a large-scale, code-submission-based competition comprising two challenges. First, the Transfer Challenge asks participants to build and test a model that can zero-shot decode new tasks and new subjects from their EEG data. Second, the Psychopathology factor prediction Challenge asks participants to infer subject measures of mental health from EEG data. For this, we use an unprecedented, multi-terabyte dataset of high-density EEG signals (128 channels) recorded from over 3,000 child to young adult subjects engaged in multiple active and passive tasks. We provide several tunable neural network baselines for each of these two challenges, including a simple network and demographic-based regression models. Developing models that generalise across tasks and individuals will pave the way for ML network architectures capable of adapting to EEG data collected from diverse tasks and individuals. Similarly, predicting mental health-relevant personality trait values from EEG might identify objective biomarkers useful for clinical diagnosis and design of personalised treatment for psychological conditions. Ultimately, the advances spurred by this challenge could contribute to the development of computational psychiatry and useful neurotechnology, and contribute to breakthroughs in both fundamental neuroscience and applied clinical research.

Problem

• Develop EEG models generalizing across tasks and subjects
• Predict mental health traits from EEG data
• Create scalable EEG decoding for diverse clinical applications

Innovation

• Large-scale EEG dataset with 3000+ subjects
• Zero-shot decoding for new tasks and subjects
• Neural network baselines for psychopathology prediction