Trading off Quality for Efficiency of Community Detection: An Inductive Method across Graphs

TL;DR

This paper introduces an inductive community detection method using adversarial dual GNNs that generalizes across graphs, balancing quality and efficiency better than existing transductive approaches.

Contribution

The paper proposes a novel inductive community detection approach that leverages offline training on historical graphs to enable fast, high-quality detection on unseen graphs without additional optimization.

Findings

ICD achieves a better trade-off between quality and efficiency.

The method generalizes well to unseen graphs with varying sizes.

Experiments show significant improvements over baseline methods.

Abstract

Many network applications can be formulated as NP-hard combinatorial optimization problems of community detection (CD). Due to the NP-hardness, to balance the CD quality and efficiency remains a challenge. Most existing CD methods are transductive, which are independently optimized only for the CD on a single graph. Some of these methods use advanced machine learning techniques to obtain high-quality CD results but usually have high complexity. Other approaches use fast heuristic approximation to ensure low runtime but may suffer from quality degradation. In contrast to these transductive methods, we propose an alternative inductive community detection (ICD) method across graphs of a system or scenario to alleviate the NP-hard challenge. ICD first conducts the offline training of an adversarial dual GNN on historical graphs to capture key properties of the system. The trained model is then directly generalized to new unseen graphs for online CD without additional optimization, where a better trade-off between quality and efficiency can be achieved. ICD can also capture the permutation invariant community labels in the offline training and tackle the online CD on new graphs with non-fixed number of nodes and communities. Experiments on a set of benchmarks demonstrate that ICD can achieve a significant trade-off between quality and efficiency over various baselines.