General Community Detection in Attributed Networks with Consistent-Module Constrained Nonnegative Matrix Factorization

Figure 2

Convergence curve of our proposed GCDNMF. The horizontal axis is the number of iterations, and the vertical axis is the difference of the objective function values. The value of the vertical axis gradually decreases to close to 0, indicating that the algorithm converges.

(a) Cora

(b) Citeseer

(c) Cornell

(d) Texas

(e) Washington

(f) Wisconsin