Research map / Label-efficient and robust learning / Domain adaptation and generalization
Side Information Dependence as a Regularizer for Analyzing Human Brain Conditions across Cognitive Experiments
Shuo Zhou, Wenwen Li, Christopher Cox, Haiping Lu
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 SIDeR-SVM instead of ARSVM (MMD-based) on multi-source tasks | SIDeR-SVM · Brain decoding TL, 3 multi-source tasks avg | accuracy (%): 67.6 -> 83.2 | Improved |
| use HSIC dependence on experiment and subject covariates instead of MMD (MIDA vs TCA) | MIDA · Brain decoding TL, single-source avg | accuracy (%): 63.4 -> 68.0 | Improved |
| use hinge prediction loss instead of label dependence (SIDeR vs SMIDA) | SIDeR-SVM · Brain decoding TL, single-source avg | accuracy (%): 59.1 -> 78.8 | Improved |
| use SIDeR-SVM instead of best baseline on A→B | SIDeR-SVM · A→B | accuracy (%): 65.7 -> 78.6 | Improved |
| add multiple sources (A&B→C) versus single source B→C | SIDeR-SVM · target C | accuracy (%): 90.5 -> 89.9 | Mixed |
| set lambda=0 (remove domain dependence regulariser) (ablation) | SIDeR-SVM · Brain decoding TL | accuracy | Hurt |
| vary lambda over positive values (ablation) | SIDeR-SVM · Brain decoding TL | accuracy | No clear effect |
| increase C from 1 to 10^4 (ablation) | SIDeR-SVM · Brain decoding TL | accuracy | Hurt |
| use conditional distribution alignment (JDA, MEDA) over marginal alignment | JDA/MEDA · Brain decoding TL | accuracy: 58.2/60.6 vs 63.4/67.5 avg | Hurt |
Closest papers by meaning
- MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data (ICML 2025 · similarity 0.86)
- Semi-supervised Deep Transfer for Regression without Domain Alignment (ICCV 2025 · similarity 0.86)
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.85)
- MindBridge: A Cross-Subject Brain Decoding Framework (CVPR 2024 · similarity 0.85)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.84)
- BrainLM: A foundation model for brain activity recordings (ICLR 2024 · 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.
