AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training

Yuting Tang, Weibang Jiang, Shanglin Li, Yong Li, Chenyu Liu, Xinliang Zhou, Yi Ding, Cuntai Guan

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
distill pre-training data to 5% with EEG-DLite instead of random 5%LaBraM-base pre-training · SEED-Vaccuracy (%): 34.6 -> 38.6Improved
distill to 1% with EEG-DLite instead of randomLaBraM-base pre-training · SEED-Vaccuracy (%): 26.5 -> 29.7Improved
distill to 5% with EEG-DLite instead of full dataLaBraM-base pre-training · TUAB / TUEV / MoBIdownstream performance: MoBI PCC 0.538 -> 0.550; TUEV F1 83.1 -> 82.2 at 10%Mixed
use synthetic data generation (M3D) instead of random selectionEEG pre-training distillation · SEED-Vaccuracy (%): 34.6 -> 26.9 at 5%Hurt
use SSL autoencoder embeddings instead of PCA for diversity sampling (ablation)EEG-DLite · SEED-Vaccuracy (%): 31.0 -> 38.6 at 5%Improved
add outlier removal (tau = 1%) before diversity sampling (ablation)EEG-DLite with EEGNet · SEED cross-subject supervised (50% data)accuracy (%): 54.1 -> 56.6Improved
add outlier removal (tau = 1%) (ablation)EEG-DLite with EEGNet · SEED cross-subject supervised (25% data)accuracy (%): 54.6 -> 55.3Improved
remove top 0.05% OOD samples before selection (ablation)EEG-DLite pre-training · SEED-VaccuracyImproved
distill to 25% with EEG-DLite instead of full dataEEGNet supervised · SEED cross-subjectaccuracy (%): 54.6 -> 55.3Improved
increase distillation ratio for random selection from 5% to 25% (ablation)Random baseline · SEED-Vaccuracy (%): 34.6 -> 39.1Improved
increase distillation ratio from 10% to 25% for EEG-DLite (ablation)EEG-DLite · TUABAUROC (%): 90.8 -> 90.3No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy