Graph-based Semi-supervised Local Clustering with Few Labeled Nodes

TL;DR

This paper introduces a semi-supervised local clustering method on graphs that leverages few labeled nodes and improves initial cut quality, demonstrating effectiveness across multiple datasets.

Contribution

It proposes a novel semi-supervised local clustering approach that enhances initial cut quality by considering the entire graph, overcoming limitations of previous methods.

Findings

Effective clustering on various datasets

Improved initial cut quality

Outperforms existing semi-supervised methods

Abstract

Local clustering aims at extracting a local structure inside a graph without the necessity of knowing the entire graph structure. As the local structure is usually small in size compared to the entire graph, one can think of it as a compressive sensing problem where the indices of target cluster can be thought as a sparse solution to a linear system. In this paper, we apply this idea based on two pioneering works under the same framework and propose a new semi-supervised local clustering approach using only few labeled nodes. Our approach improves the existing works by making the initial cut to be the entire graph and hence overcomes a major limitation of the existing works, which is the low quality of initial cut. Extensive experimental results on various datasets demonstrate the effectiveness of our approach.