Table 2 Statistics on the impact of adding spurious interactions to the Yeast-D1 dataset.
Noise | \(Add_{Random}\) | \(Add_{HighDegree}\) | \(Add_{LowDegree}\) | ||||||
|---|---|---|---|---|---|---|---|---|---|
m | \(\vert n \vert _{d=1}\) | \(d_{Avg}\) | m | \(\vert n \vert _{d=1}\) | \(d_{Avg}\) | m | \(\vert n \vert _{d=1}\) | \(d_{Avg}\) | |
0% | 4687 | 28 | 9.4687 | 4687 | 28 | 9.4687 | 4687 | 28 | 9.4687 |
10% | 5189 | 28 | 10.4828 | 5065 | 21 | 10.2323 | 4778 | 20 | 9.6525 |
20% | 5689 | 28 | 11.4929 | 5443 | 15 | 10.9959 | 4868 | 10 | 9.8343 |
30% | 6179 | 28 | 12.4828 | 5821 | 13 | 11.7595 | 4959 | 7 | 10.0181 |
40% | 6684 | 28 | 13.5030 | 6199 | 5 | 12.5232 | 5049 | 6 | 10.2 |
50% | 7147 | 28 | 14.4383 | 6578 | 5 | 13.2888 | 5140 | 4 | 10.3838 |
