Research map / Graph learning / Graph algorithms and clustering
SimiNet: A Novel Method for Quantifying Brain Network Similarity
Ahmad Mheich, Mahmoud Hassan, Mohamad Ali Khalil, Vincent Gripon, Olivier Dufor, Fabrice Wendling
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 |
|---|---|---|---|
| account for node spatial location (SimiNet vs location-blind baselines) | graph similarity · Simulated graphs, node position shifts | similarity index: 0.7825 ± 0.05 -> 0.095 ± 0.007 | Improved |
| increase edge weights under SimiNet | SimiNet · Simulated graphs, edge weight alteration | similarity index | Improved |
| increase edge weights under DeltaCon | DeltaCon · Simulated graphs, edge weight alteration | similarity index: 1.0 to 0.27 ± 0.07 | Hurt |
| increase edge weights under Lambda distance | Lambda distance · Simulated graphs, edge weight alteration | similarity index: 1 to 0.05 ± 0.02 | Hurt |
| alter edge weights for GED and VEO | GED, VEO · Simulated graphs, edge weight alteration | similarity index: similarity=1 | No clear effect |
| insert nodes in altered graph | SimiNet · Simulated graphs, node insertion | similarity index: 0.947 ±0.006 -> 0.73 ± 0.005 | Improved |
| insert nodes in altered graph | VEO · Simulated graphs, node insertion | similarity index: 0.9705 ± 0.01 -> 0.91 ± 0.02 | Mixed |
| shift node positions for kernel methods | spkernel, WL, WLspdelta, RWkernel · Simulated graphs, node position shifts | similarity index: 0.917 ± 0.001; 0.991 ± 0.013; 0.932 ± 0.012; 0.99 ± 0.001 | No clear effect |
| edge weight alteration for WL, spkernel, WLspdelta kernels | graph kernels · Simulated graphs, edge weight alteration | similarity index: similarity=1 | No clear effect |
| move from visual processing to memory access window | SimiNet · Real EEG networks, objects vs animals | median similarity: 0.1 -> 0.03 | Improved |
| move from visual processing to memory access window | DeltaCon · Real EEG networks, objects vs animals | median similarity: 0.22 -> 0.21 | No clear effect |
| move from visual processing to memory access window | GED · Real EEG networks, objects vs animals | median similarity: 0.14 -> 0.12 | No clear effect |
Closest papers by meaning
- A Neurobiological Evaluation Metric for Neural Network Model Search (CVPR 2019 · similarity 0.87)
- Brain Network Transformer (NeurIPS 2022 · similarity 0.87)
- Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention (NeurIPS 2021 · similarity 0.86)
- Long-range Brain Graph Transformer (NeurIPS 2024 · similarity 0.86)
- Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory (ICLR 2024 · similarity 0.84)
- BrainOOD: Out-of-distribution Generalizable Brain Network Analysis (ICLR 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.
