Silencer: Robust Community Detection by Silencing of Noisy Pixels

TL;DR

Silencer is a novel framework that enhances community detection robustness by silencing noisy pixels in the adjacency matrix, improving performance across various network types and noise conditions.

Contribution

It introduces a flexible noise-silencing approach for community detection, with theoretical convergence proof for NMF and superior empirical performance.

Findings

Top performance on six real-world networks with different noise types

Effective across ER, BA, and WS network models

Convergence of the proposed method is theoretically proven

Abstract

Real-world networks carry all kinds of noise, resulting in numerous challenges for community detection. Further improving the performance and robustness of community detection has attracted significant attention. This paper considers edge noise, which causes edges in the network to be added or removed. Existing methods achieve graph denoising through link prediction or robustness in low eigenvectors. However, they are either limited in application scenarios or not determined for effectiveness. We find that the noisy pixel in the adjacency matrix has a certain proportion in the loss function, which makes the optimization of the community detection model seriously deviate from the correct direction. Thus, we design an flexible framework to silence the contribution of noisy pixels to loss function, called Silencer. We take the nonnegative matrix factorization (NMF) and deep NMF methods as examples since they are the prime models for community detection. We first prove the convergence of Silencer in NMF. Compared with existing methods, Silencer show top performance in six real-world networks with random noise, adversarial perturbation, and mixed noise. Moreover, Silencer works on random (ER), scale-free (BA), and small-world (WS) networks, and the improvement of Silencer is gradually insignificant in the order ER, BA, and WS networks.