Research map / Graph learning / Graph self-supervised learning
EpiTwin: Spatiotemporal Graph Transformers for Epileptic sEEG Signal Reconstruction
Jingbo Yang, Yunfeng Zhao, Chao Qiu, Yulin Sun, Xiuyun Liu, Xiaofei Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use EpiTwin instead of strongest baseline LaBraM | sEEG reconstruction · sEEG reconstruction, single patient | RMSE: 0.591 -> 0.492 | Improved |
| use EpiTwin instead of LaBraM | sEEG reconstruction · sEEG reconstruction, single patient | LSD / High-LSD: LSD 0.541 -> 0.463; High-LSD 0.525 -> 0.449 | Improved |
| combine geometric, topological and positional encodings (HSPE) rather than a single source (ablation) | EpiTwin · sEEG reconstruction, single patient | RMSE: about 0.51 -> 0.492 | Improved |
| use geometry-functional biased attention rather than vanilla attention (ablation) | EpiTwin · sEEG reconstruction, single patient | RMSE: 0.5220 -> 0.4920 | Improved |
| use geometry-functional biased attention rather than graph k-NN attention (ablation) | EpiTwin · sEEG reconstruction, single patient | LSD: 0.4877 -> 0.4630 | Improved |
| add adversarial refinement stage (ablation) | EpiTwin · sEEG reconstruction, single patient | LSD / High-LSD | Improved |
| use EpiTwin instead of LaBraM with two patients | sEEG reconstruction · sEEG reconstruction, two patients | LSD: 0.6984 -> 0.6986 | No clear effect |
| use EpiTwin instead of LaBraM with five patients | sEEG reconstruction · sEEG reconstruction, five patients | RMSE: 0.6080 -> 0.5773 | Improved |
| use EpiTwin instead of LaBraM on unseen patient | sEEG reconstruction · sEEG reconstruction, leave-one-subject-out | RMSE: 1.253 -> 0.956 | Improved |
| evaluate with temporally contiguous split instead of random split | EpiTwin · sEEG reconstruction | RMSE: 0.492 -> 0.504 | Hurt |
| add more subjects to the training data | all methods · sEEG reconstruction | RMSE: EpiTwin 0.4920 (1 patient) -> 0.5773 (5 patients) | Hurt |
Closest papers by meaning
- Neural decoding from stereotactic EEG: accounting for electrode variability across subjects (NeurIPS 2024 · similarity 0.87)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (NeurIPS 2024 · similarity 0.85)
- EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals (NeurIPS 2024 · similarity 0.84)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.84)
- What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment (NeurIPS 2026 · similarity 0.84)
- EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
