Inductive Attributed Community Search: to Learn Communities across Graphs

Attributed community search (ACS) aims to identify subgraphs satisfying both structure cohesiveness and attribute homogeneity in attributed graphs, for a given query that contains query nodes and query attributes. Previously, algorithmic approaches deal with ACS in a two-stage paradigm, which suffer from structural inflexi¬bility and attribute irrelevance. To overcome this problem, recently, learning-based approaches have been proposed to learn both struc¬tures and attributes simultaneously as a one-stage paradigm. How¬ever, these approaches train a transductive model which assumes the graph to infer unseen queries is as same as the graph used for training. That limits the generalization and adaptation of these approaches to different heterogeneous graphs. In this paper, we propose a new framework, Inductive Attributed Community Search, LACS, by inductive learning, which can be used to infer new queries for different communities/graphs. Specifically, LACS employs an encoder-decoder neural architecture to handle an ACS task at a time, where a task consists of a graph with only a few queries and corresponding ground-truth. We design a three-phase workflow, “training-adaptation-inference, which learns a shared model to absorb and induce prior effective common knowledge about ACS across different tasks. And the shared model can swiftly adapt to a new task with small number of ground-truth. We conduct substantial experiments in 7 real-world datasets to verify the effec¬tiveness of LACS for CS/ACS. Our approach LACS achieves 28.97% and 25.60% improvements in FI-score on average in CS and ACS, respectively.