Research map / Probabilistic and scientific modeling / Dynamical systems
Parameter-Free Centralized Multi-Task Learning for Characterizing Developmental Sex Differences in Resting State Functional Connectivity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add task weights and centralized regularization (Proposed vs MKL) (ablation) | multi-task learning · PNC males | CC: 0.581 ± 0.016 -> 0.599 ± 0.012 | Helped |
| add task weights and centralized regularization (Proposed vs MKL) (ablation) | multi-task learning · PNC females | CC: 0.452 ± 0.028 -> 0.495 ± 0.027 | Helped |
| multi-task learning (Proposed) instead of single-group Lasso | Lasso · PNC females | CC: 0.400 ± 0.025 -> 0.495 ± 0.027 | Helped |
| multi-task learning (Proposed) instead of single-group Lasso | Lasso · PNC | CC: 12.35% | Helped |
| Proposed instead of MKL | MKL · PNC | CC: 5.82% | Helped |
| Proposed instead of MKL (ablation) | MKL · Synthetic Data 1 | CC: 0.766 ± 0.032 -> 0.799 ± 0.012 | Helped |
| Proposed instead of MKL (ablation) | MKL · Synthetic Data 2 | CC: 0.711 ± 0.015 -> 0.763 ± 0.015 | Helped |
| pool both groups into one model (concatenation) | Regression/Lasso · Synthetic Data 4 Task 2 | CC: 0.801 ± 0.027 -> 0.801 ± 0.047 | No clear effect |
| use feature selection (Lasso) instead of full regression | Regression · Synthetic Data 4 Task 1 | CC: 0.758 ± 0.054 -> 0.767 ± 0.015 | Helped |
| add group label as extra feature (MixLasso) vs Lasso | Lasso · PNC females | CC: 0.400 ± 0.025 -> 0.414 ± 0.017 | Helped |
| add group label as extra feature (MixLasso) vs Lasso | Lasso · PNC males | CC: 0.566 ± 0.014 -> 0.571 ± 0.013 | Helped |
| pool males and females (ConLasso) vs separate Lasso | Lasso · PNC males | CC: 0.566 ± 0.014 -> 0.567 ± 0.013 | No clear effect |
Closest papers by meaning
- Large Connectome Model: An fMRI Foundation Model of Brain Connectomes Empowered by Brain-Environment Interaction in Multitask Learning Landscape (AAAI 2026 · similarity 0.86)
- Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies (NeurIPS 2021 · similarity 0.85)
- SwiFT: Swin 4D fMRI Transformer (NeurIPS 2023 · similarity 0.84)
- NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders (ICML 2025 · similarity 0.83)
- Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens (NeurIPS 2025 · similarity 0.82)
- A Local-Ascending-Global Learning Strategy for Brain-Computer Interface (AAAI 2024 · similarity 0.82)
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.