Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributed

Jiang, Yu-Li; Yu, Rong; Chen, Hong; Huang, Xin; Zhao, Kangfei; Huang, Junzhou

doi:10.48550/arxiv.2104.03583

Cited by 4 publications

(7 citation statements)

References 28 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unless stated otherwise, in each layer we employ ReLU as activation function, and dropout rate of 0.5. For large datasets, we adopt the method used in [15,22] and select nodes in 2-hop neighbors of query nodes as the candidate subgraph for each query. We then train the model on these small subgraphs and predict communities.…”

Section: Methodsmentioning

confidence: 99%

“…More recently, CS has also been investigated for more complex graphs, such as directed [10,11], geo-social [16,41], temporal [29], multi-valued [28], weighted [40], and labeled [8] graphs. To address the structural inflexibility of these models, recently, graph neural network-based approaches have been introduced [15,22]. However, all these approaches focus on networks with a single view while we study networks with multiple views.…”

Section: Motivationsmentioning

confidence: 99%

See 1 more Smart Citation

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

Behrouz

Hashemi

2022

Proceedings of the 31st ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Motivationsmentioning

confidence: 99%

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

Behrouz

Hashemi

2022

Proceedings of the 31st ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…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.…”

Section: Related Workmentioning

confidence: 99%

CS-TGN: Community Search via Temporal Graph Neural Networks

Hashemi

Behrouz

Hajidehi

2023

Companion Proceedings of the ACM Web Conference 2023

View full text Add to dashboard Cite

Searching for local communities is an important research challenge that allows for personalized community discovery and supports advanced data analysis in various complex networks, such as the World Wide Web, social networks, and brain networks. The evolution of these networks over time has motivated several recent studies to identify local communities in temporal networks. Given any query nodes, Community Search aims to find a densely connected subgraph containing query nodes. However, existing community search approaches in temporal networks have two main limitations:(1) they adopt pre-defined subgraph patterns to model communities, which cannot find communities that do not conform to these patterns in real-world networks, and (2) they only use the aggregation of disjoint structural information to measure quality, missing the dynamic of connections and temporal properties. In this paper, we propose a query-driven Temporal Graph Convolutional Network (CS-TGN) that can capture flexible community structures by learning from the ground-truth communities in a data-driven manner. CS-TGN first combines the local query-dependent structure and the global graph embedding in each snapshot of the network and then uses a GRU cell with contextual attention to learn the dynamics of interactions and update node embeddings over time. We demonstrate how this model can be used for interactive community search in an online setting, allowing users to evaluate the found communities and provide feedback. Experiments on real-world temporal graphs with ground-truth communities validate the superior quality of the solutions obtained and the efficiency of our model in both temporal and interactive static settings. CCS CONCEPTS• Computing methodologies → Neural networks; • Mathematics of computing → Graph algorithms.

show abstract

“…To this end, it is quite difficult to choose a proper 𝑘 value as well as one community metric to pursue high accuracy. To tackle the structural inflexibility of traditional CS algorithms, ML/DL-based solutions [14,24] are arising as an attractive research direction. These approaches build ML/DL models from given ground-truth communities and expect the model to generalize to unknown community-member relationships.…”

Section: Introductionmentioning

confidence: 99%

“…The effectiveness will be degraded if the user cannot provide enough high-quality ground-truth for that query node. [24] proposes a graph neural network based model that is trained by a collection of query nodes with their ground-truth, and makes predictions for unseen query nodes. For one graph, a large volume of query nodes with membership ground-truth are necessary for training, which ensure the model well generalize to other local queries.…”

Section: Introductionmentioning

confidence: 99%

Community Search: A Meta-Learning Approach

Fang¹,

Zhao²,

Li³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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 groundtruth. Our experiments show that CGNP outperforms the native graph algorithms and ML baselines 147% and 113% on F1-score by average.

show abstract

Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributed

Cited by 4 publications

References 28 publications

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

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

CS-TGN: Community Search via Temporal Graph Neural Networks

Community Search: A Meta-Learning Approach

Contact Info

Product

Resources

About