Table 6 Changes of normalized mutual information on graph clustering algorithms in percentage
From: Outlier edge detection using random graph generation models and applications
\(\mu\) | LRW | GN (%) | SLM | Danon (%) | Louvain | Infomap |
|---|---|---|---|---|---|---|
0.2 | 0 | 0.8 | 0 | 1.0 | 0 | 0 |
0.25 | 3.3% | 1.5 | 0 | −1.0 | 0 | 0 |
0.3 | 7.3% | 5.0 | 0 | 3.5 | 0 | 9.1% |
0.35 | 5.7% | −2.2 | −2.1 | 26 | −4.9% | 155% |
0.4 | 8.5% | 6.7 | −2.2 | 4.8 | −3.0% | 5.8% |
0.45 | 190% | −1.1 | −6.2 | 8.4 | −12% | 95% |
0.5 | 1730% | 19 | −4.4 | 26 | 2.4% | \(\infty\) |