arXiv cs.LG + cs.RO + cs.HC· Miran \"Ozdogan, Gereon Elvers, Michael Bronstein, Oiwi Parker Jones·· 2 天前AI 评分58
arXiv 论文：训练时 logit 平均刷新非侵入式语音脑机接口最优结果
Logit Averaging During Training Sets a New State of the Art for Non-Invasive Speech BCI
AI 导读
研究团队在 arXiv 发布论文，系统比较了非侵入式神经解码中的六种多试次聚合策略，覆盖三个数据集、四项任务和两种组规模。作者提出的训练时 logit 平均在 7 个设置中的 6 个优于其他方法，并在 2025 PNPL 竞赛的音素分类设置上以平衡准确率领先竞赛冠军 17.4 个百分点。论文还把 logit 平均与联合集成训练联系起来，对后者表现不佳的既有解释提出质疑。
正文 · 原文
Abstract:Non-invasive brain-computer interfaces are in practice limited by signal-to-noise ratio, and recent state-of-the-art methods address this limitation by aggregating over repeated trials of the same stimulus. Yet multi-trial aggregation has been treated inconsistently across the literature: some work averages brain signals at the model's input, other work averages predictions at the model's output, and neither treats aggregation as an architectural choice in its own right. We provide the first systematic comparison of aggregation strategies for non-invasive neural decoding, evaluating six paradigms (including logit averaging during training and three attention-based variants we introduce) across three datasets, four tasks, and two group sizes. We find that aggregation choice matters substantially: training-time logit averaging, the simplest method we propose, outperforms all others in 6 of 7 settings. On the phoneme classification setting of the 2025 PNPL competition, it sets a new state of the art, significantly outperforming the competition winner by 17.4 absolute percentage points in balanced accuracy. We further draw a theoretical connection between logit averaging and joint ensemble training, which has been shown to underperform independent ensembling in the deep learning literature; our results call into question recent explanations of why joint ensemble training fails. Together, these findings establish multi-trial aggregation as a key design choice for non-invasive neural decoding and identify training-time logit averaging as a simple, effective default.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.26347 [cs.LG] |
| (or arXiv:2610.26347v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.26347 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Miran Özdogan [view email]
[v1]
Mon, 19 Oct 2026 13:13:25 UTC (1,042 KB)
来源：arXiv cs.LG + cs.RO + cs.HC · arxiv.org