Bounded Projection Matrix Approximation with Applications to Community Detection
This work addresses community detection in unsupervised learning, presenting an incremental improvement with a new algorithmic approach.
The paper tackled the community detection problem by proposing a projection matrix approximation method with entrywise bounded constraints, achieving superior performance over competitors like semi-definite relaxation and spectral clustering in numerical experiments.
Community detection is an important problem in unsupervised learning. This paper proposes to solve a projection matrix approximation problem with an additional entrywise bounded constraint. Algorithmically, we introduce a new differentiable convex penalty and derive an alternating direction method of multipliers (ADMM) algorithm. Theoretically, we establish the convergence properties of the proposed algorithm. Numerical experiments demonstrate the superiority of our algorithm over its competitors, such as the semi-definite relaxation method and spectral clustering.