# A Composable Channel-Adaptive Architecture for Seizure Classification

arXiv: https://arxiv.org/abs/2512.19123 · HTML: https://mlsanity.com/paper/2512.19123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 22 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Temporal Convolutional Networks: A Unified Approach to Action Segmentation](https://mlsanity.com/paper/1608.08242/) (2016)
- [BrainBERT: Self-supervised representation learning for intracranial recordings](https://mlsanity.com/paper/2302.14367/) (2023)
- [Self-Supervised Learning for Anomalous Channel Detection in EEG Graphs: Application to Seizure Analysis](https://mlsanity.com/paper/2208.07448/) (2022)
- [2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets](https://mlsanity.com/paper/2202.12950/) (2022)
- [Deep Convolutional Neural Networks for Interpretable Analysis of EEG Sleep Stage Scoring](https://mlsanity.com/paper/1710.00633/) (2017)
- [One-shot Learning for iEEG Seizure Detection Using End-to-end Binary Operations: Local Binary Patterns with Hyperdimensional Computing](https://mlsanity.com/paper/1809.01926/) (2018)
- [Functional Neural Networks: Shift invariant models for functional data with applications to EEG classification](https://mlsanity.com/paper/2301.05869/) (2023)

## Abstract (arXiv)

Objective: We develop a channel-adaptive (CA) architecture that seamlessly processes multi-variate time-series with an arbitrary number of channels, and in particular intracranial electroencephalography (iEEG) recordings. Methods: Our CA architecture first processes the iEEG signal using state-of-the-art models applied to each single channel independently. The resulting features are then fused using a vector-symbolic algorithm which reconstructs the spatial relationship using a trainable scalar per channel. Finally, the fused features are accumulated in a long-term memory of up to 2 minutes to perform the classification. Each CA-model can then be pre-trained on a large corpus of iEEG recordings from multiple heterogeneous subjects. The pre-trained model is personalized to each subject via a quick fine-tuning routine, which uses equal or lower amounts of data compared to existing state-of-the-art models, but requiring only 1/5 of the time. Results: We evaluate our CA-models on a seizure detection task both on a short-term (~20 hours) and a long-term (~2500 hours) dataset. In particular, our CA-EEGWaveNet is trained on a single seizure of the tested subject, while the baseline EEGWaveNet is trained on all but one. Even in this challenging scenario, our CA-EEGWaveNet surpasses the baseline in median F1-score (0.78 vs 0.76). Similarly, CA-EEGNet based on EEGNet, also surpasses its baseline in median F1-score (0.79 vs 0.74). Conclusion and significance: Our CA-model addresses two issues: first, it is channel-adaptive and can therefore be trained across heterogeneous subjects without loss of performance; second, it increases the effective temporal context size to a clinically-relevant length. Therefore, our model is a drop-in replacement for existing models, bringing better characteristics and performance across the board.