Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Algorithm 1: Semi-supervised community detection algorithm based on must-link and cannot-link constraints.

More »

Table 1 Expand

Figure 1.

A simple two-community network.

If the nodes are selected according to their degree values, only node will be selected, and community will be ignored. However, using the score value in conjunction with degree value of every node in the network as the condition, we will select node (or ) from the network at least, which means that the selected nodes can cover all of the ground truth communities. (The different node shapes and shades indicate different communities, the black lines are the edges within communities, and the light-gray connections represent the edges across different communities. This illustration style is also applied in the following figures.)

More »

Figure 1 Expand

Table 2.

Algorithm 2: Active approach to generate the must-link and cannot-link constraints.

More »

Table 2 Expand

Table 3.

Algorithm 3: .

More »

Table 3 Expand

Table 4.

Algorithm 4: Similarity computation algorithm based on random walk.

More »

Table 4 Expand

Table 5.

Statistical information of the networks.

More »

Table 5 Expand

Figure 2.

Zachary's karate club network.

(a) The ground truth community structure; (b) The community structure extracted by the proposed algorithm; (c) The community structure extracted by FastQ; (d) The community structure aggregated from 30 community structures extracted by LPA; (e) The community structure detected by Infohiermap; (f) The community structure identified by PPC.

More »

Figure 2 Expand

Table 6.

Comparisons of the 3 metrics: A rank (number in parentheses) is attached to the value of each metric for each network, and the value with the highest rank for each metric on each network is shown in bold.

More »

Table 6 Expand

Figure 3.

Lusseau's bottlenose dolphin social network.

(a) The ground truth community structure; (b) The community structure extracted by the proposed algorithm; (c) The community structure identified by FastQ; (d) The community structure aggregated from 30 outputs of LPA; (e) The community structure detected by Infohiermap; (f) The community structure identified by PPC.

More »

Figure 3 Expand

Figure 4.

Risk map network.

(a) The ground truth community structure; (b) The community structure identified by the proposed algorithm; (c) The community structure extracted by FastQ; (d) The community structure aggregated from 30 outputs of LPA; (e) The community structure detected by Infohiermap; (f) The community structure extracted by PPC.

More »

Figure 4 Expand

Figure 5.

Collaboration network of scientists at the Santa Fe Institute.

(a) The ground truth community structure; (b) The community structure detected by the proposed algorithm; (c) The community structure obtained by FastQ; (d) The community structure aggregated from 30 results of LPA; (e) The first-level community structure extracted by Infohiermap; (f) The second-level community structure extracted by Infohiermap; (g) The community structure identified by PPC.

More »

Figure 5 Expand

Figure 6.

The evolutions of the three metrics on the dolphin social network.

More »

Figure 6 Expand

Figure 7.

The evolutions of the three metrics on the scientist collaboration network.

More »

Figure 7 Expand