Community Search: Learn from Small Data
share
Community Search (CS) is one of the fundamental graph analysis tasks, which is a building block of various real applications. Given any query nodes, CS aims to find cohesive subgraphs that query nodes belong to. Recently, a large number of CS algorithms are designed. These algorithms adopt pre-defined subgraph patterns to model the communities, which cannot find communities that do not have such pre-defined patterns in real-world graphs. Thereby, machine learning based approaches are proposed to capture flexible community structures by learning from community ground-truth in a data-driven fashion. However, existing approaches rely on sufficient training data to provide enough generalization for machine learning models. In this paper, we study ML-based approaches for community search, under the circumstance that the training data is scarce. To learn from small data, we extract prior knowledge which is shared across different graphs as CS tasks in advance. Subsequent small training data from a new CS task are combined with the learned prior knowledge to help the model well adapt to that specific task. A novel meta-learning based framework, called CGNP, is designed and implemented to fulfill this learning procedure. A meta CGNP model is a task-common node embedding function for clustering by nature, learned by metric-based learning. To the best of our knowledge, CGNP is the first meta model solution for CS. We compare CGNP with traditional CS algorithms, e.g., CTC, ATC, ACQ, and ML baselines on real graph datasets with ground-truth. Our experiments show that CGNP outperforms the native graph algorithms and ML baselines 147
READ FULL TEXT