CS-MLGCN: Multiplex Graph Convolutional Networks for Community Search in Multiplex Networks

Abstract

Community Search (CS) is one of the fundamental tasks in network science and has attracted much attention due to its ability to discover personalized communities with a wide range of applications. Given any query nodes, CS seeks to find a densely connected subgraph containing query nodes. Most existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in many applications such as biological, social, and transportation networks, interactions between objects span multiple aspects, yielding networks with multiple views, called multiplex networks. Existing CS approaches in multiplex networks adopt pre-defined subgraph patterns to model the communities, which cannot find communities that do not have such pre-defined patterns in real-world networks. In this paper, we propose a query-driven graph convolutional network in multiplex networks, CS-MLGCN, that can capture flexible community structures by learning from the ground-truth communities in a data-driven fashion. CS-MLGCN first combines the local query-dependent structure and global graph embedding in each type of proximity and then uses an attention mechanism to incorporate information on different types of relations. Experiments on real-world graphs with ground-truth communities validate the quality of the solutions we obtain and the efficiency of our model. CCS CONCEPTS• Computing methodologies → Neural networks; • Mathematics of computing → Graph algorithms.

CS-TGN: Community Search via Temporal Graph Neural Networks

“…We used ReLU as the activation function and a dropout rate of 0.5. When dealing with large datasets, we follow the approach outlined in [3,18,25] and choose nodes within 2-hops of query nodes as possible subgraphs for each query. The model is then trained on these subgraphs to predict communities.…”

“…Truss [49] is an approach based on 𝑘-truss structure in temporal networks. MLGCN [3] is a learningbased CS method in multiplex networks that leverages an attention mechanism to incorporate the information of different relation types. FTCS [4] finds the connected FirmTruss containing query nodes with the minimum diameter.…”

“…Since then, various community models have been proposed based on different pre-defined dense subgraphs [13], including 𝑘-core [40,41], 𝑘-truss [2,23], quasi-clique [11], 𝑘-plex [48], and densest subgraph [53]. Recently, community search has also been explored in directed [14,15], weighted [55], geo-social [21,56], multilayer [3,4,24], multi-valued [27], and labeled [12] graphs. Inspired by the success of Graph Neural Networks (GNNs), recently, several GNN-based approaches have been proposed for community search, such as [3,18,25].…”

“…Recently, community search has also been explored in directed [14,15], weighted [55], geo-social [21,56], multilayer [3,4,24], multi-valued [27], and labeled [12] graphs. Inspired by the success of Graph Neural Networks (GNNs), recently, several GNN-based approaches have been proposed for community search, such as [3,18,25]. However, these models only focus on static networks and do not capture the dynamics of interactions and temporal properties.…”

“…However, these models have limitations in both their design and training strategies [51]. To overcome these limitations, recent frameworks such as ROLAND and its variants [5,51] have been proposed to re-purpose static GNNs for dynamic graphs. However, these approaches only incorporate node embeddings from the previous snapshot in the GRU cell, failing to capture short-term patterns.…”