Research map / Learning theory and algorithms / Clustering
Discovering conflicting groups in signed networks
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 |
|---|---|---|---|
| use SCG-MA spectral rounding instead of KOCG-top-1 | SCG · WoW-EP8, k=2 | polarity objective: 9.0 -> 236.6 | Helped |
| use SCG-MA instead of BNC-k | SCG · WoW-EP8, k=2 | polarity objective: 184.6 -> 236.6 | Helped |
| use SCG-MA instead of SPONGE-k | SCG · Referendum, k=2 | polarity objective: 41.5 -> 172.2 | Helped |
| round with randomized rounding (SCG-R) instead of minimum angle (SCG-MA) | SCG · Bitcoin, k=2 | polarity objective: 28.8 -> 14.9 | Hurt |
| use Bansal-pivot rounding (SCG-B) instead of minimum angle (SCG-MA) | SCG · WikiVot, k=2 | polarity objective: 71.5 -> 37.6 | Hurt |
| use maximum-objective rounding (SCG-MO) instead of minimum angle (SCG-MA) | SCG · real-world graphs | polarity objective: 236.6 vs 236.6 (WoW-EP8, k=2) | No clear effect |
| detect k+1 clusters and drop the largest instead of detecting k clusters | BNC · real-world graphs | polarity objective: 184.6 -> -0.7 (WoW-EP8, k=2) | Hurt |
| use SPONGE-(k+1) instead of SCG on synthetic m-SSBM | SPONGE · m-SSBM, n=2000, k=6 | F1 score | Mixed |
Closest papers by meaning
- An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks (NeurIPS 2025 · similarity 0.93)
- Discovering Opinion Intervals from Conflicts in Signed Graphs (NeurIPS 2025 · similarity 0.90)
- Sublinear-Time Clustering Oracle for Signed Graphs (ICML 2022 · similarity 0.87)
- Signed Laplacians for Constrained Graph Clustering (ICML 2025 · similarity 0.84)
- Optimal Quasi-clique: Hardness, Equivalence with Densest-k-Subgraph, and Quasi-partitioned Community Mining (AAAI 2024 · similarity 0.83)
- On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models (NeurIPS 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.