AI 中文总结
本文提出EEG-Arena基准，通过20,000次评估证明EEG基础模型优于监督基线，且预训练数据扩展是提升性能的关键方向。
AI 中文摘要
脑电图（EEG）基础模型（FMs）有望提供可迁移的神经表征，然而它们相对于强大的监督基线模型的优势以及进一步扩展的前景仍不明确。为解决这些问题，我们推出了EEG-Arena，一个开源基准测试平台，涵盖30个EEG基础模型和25个监督基线模型，在来自23个公共数据集的57个下游任务上进行了评估。通过跨越五种实验协议的超过20,000次评估，我们评估了下游性能、预训练收益、模型规模扩展、预训练数据扩展以及对通道配置的鲁棒性。我们发现：（1）EEG基础模型在大多数评估任务上优于强大的任务特定监督基线模型，尤其是在非双极设置下；（2）与从零开始的架构匹配的监督训练相比，预训练改善了早期优化和最终下游性能，随着更多有标签的下游数据变得可用，收益更大且更一致；（3）现有的EEG基础模型在参数数量与下游性能之间并未表现出一致的正相关关系；（4）在固定架构下，增加预训练数据规模可带来持续的下游收益；（5）通道灵活的基础模型在大多数评估的通道配置下实现了比通道受限模型更高的绝对性能。综合来看，这些发现证明了EEG基础模型的下游价值，并指出预训练数据扩展是进一步进展的有前景方向。为支持持续研究，我们发布了EEG-Arena作为开源评估框架，为可复现的基准测试、模型比较和社区驱动开发提供共享基础设施。
英文摘要
Electroencephalography (EEG) foundation models (FMs) promise transferable neural representations, yet their advantages over strong supervised baselines and their prospects for further scaling remain unclear. To address these questions, we introduce EEG-Arena, an open-source benchmark covering 30 EEG FMs and 25 supervised baselines evaluated on 57 downstream tasks from 23 public datasets. Through more than 20,000 evaluations across five experimental protocols, we assess downstream performance, pretraining benefits, model size scaling, pretraining data scaling, and robustness to channel configuration. We find that (1) EEG FMs outperform strong task-specific supervised baselines on most evaluated tasks, particularly under non-bipolar settings; (2) compared with architecture-matched supervised training from scratch, pretraining improves both early optimization and final downstream performance, with larger and more consistent gains as more labeled downstream data become available; (3) existing EEG FMs do not exhibit a consistent positive relationship between parameter count and downstream performance; (4) under a fixed architecture, increasing the pretraining data scale yields sustained downstream gains; and (5) channel-flexible FMs achieve higher absolute performance than channel-constrained models across most evaluated channel configurations. Together, these findings demonstrate the downstream value of EEG FMs and identify pretraining data expansion as a promising direction for further progress. To support continued research, we release EEG-Arena as an open-source evaluation framework that provides shared infrastructure for reproducible benchmarking, model comparison, and community-driven development.
Comments91 pages, including appendices and supplementary material
