Research map / Graph learning / Graph self-supervised learning
SnapNETS: Automatic Segmentation of Network Sequences with Node Labels
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 |
|---|---|---|---|
| extract features from Act-snapshots instead of summarized C-graphs (SN-ORIG) (ablation) | SNAPNETS · AS-PA | F1 score: 1 -> 0 | Hurt |
| SN-ORIG on AS-COM (ablation) | SNAPNETS · AS-COM | F1 score: 0.67 -> 0 | Hurt |
| SN-ORIG on Higgs (ablation) | SNAPNETS · Higgs | F1 score: 1 -> 0 | Hurt |
| SN-ORIG on BA-degree (ablation) | SNAPNETS · BA-degree | F1 score: 1 -> 1 | No clear effect |
| use Longest Path instead of ALP (SN-LP) (ablation) | SNAPNETS · Portland | F1 score: 1 -> 0.4 | Hurt |
| use Longest Path instead of ALP (SN-LP) (ablation) | SNAPNETS · Higgs | F1 score: 1 -> 0.15 | Hurt |
| use greedy edge selection instead of ALP (SN-GREEDY) (ablation) | SNAPNETS · AS-COM | F1 score: 0.67 -> 0.5 | Hurt |
| use greedy edge selection instead of ALP (SN-GREEDY) (ablation) | SNAPNETS · AS-MIX | F1 score: 0.86 -> 0.57 | Hurt |
| use greedy edge selection instead of ALP (SN-GREEDY) (ablation) | SNAPNETS · Portland | F1 score: 1 -> 1 | No clear effect |
| use greedy edge selection instead of ALP (SN-GREEDY) (ablation) | SNAPNETS · AS-PA | F1 score: 1 -> 0.67 | Hurt |
| compare SNAPNETS with VOG | SNAPNETS · AS-MIX | F1 score: 0 -> 0.86 | Helped |
| compare SNAPNETS with DYNAMMO | SNAPNETS · Higgs | F1 score: 0 -> 1 | Helped |
Closest papers by meaning
- GASP, a Generalized Framework for Agglomerative Clustering of Signed Graphs and Its Application to Instance Segmentation (CVPR 2022 · similarity 0.85)
- Interpretable Clustering on Dynamic Graphs with Recurrent Graph Neural Networks (AAAI 2021 · similarity 0.85)
- Approximating Optimal Labelings for Temporal Connectivity (AAAI 2025 · similarity 0.84)
- TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs (NeurIPS 2024 · similarity 0.84)
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models (ICML 2018 · similarity 0.84)
- Local Graph Clustering with Noisy Labels (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.