Unsupervised Learning of Node Embeddings by Detecting Communities
We present Deep MinCut (DMC), an unsupervised approach to learn node embeddings for graph-structured data. It derives node representations based on their membership in communities. As such, the embeddings directly provide interesting insights into the graph structure, so that the separate node clustering step of existing methods is no longer needed. DMC learns both, node embeddings and communities, simultaneously by minimizing the mincut loss, which captures the number of connections between communities. Striving for high scalability, we also propose a training process for DMC based on minibatches. We provide empirical evidence that the communities learned by DMC are meaningful and that the node embeddings are competitive in different node classification benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringNode ClassificationNode ClusteringSimilar Papers 제목 키워드 기반
Dynamic Network Embeddings for Network Evolution Analysis
Network embeddings learn to represent nodes as low-dimensional vectors to preserve the proximity between nodes and communities of the network for network analysis. The temporal edges (e.g., relationships, contacts, and e…
Link PredictionNetwork EmbeddingDBGDGM: Dynamic Brain Graph Deep Generative Model
Graphs are a natural representation of brain activity derived from functional magnetic imaging (fMRI) data. It is well known that clusters of anatomical brain regions, known as functional connectivity networks (FCNs), en…
Dynamic Link PredictionFunctional ConnectivityGraph ClassificationGraph Generation+2Hybrid Graph Embeddings and Louvain Algorithm for Unsupervised Community Detection
This paper proposes a novel community detection method that integrates the Louvain algorithm with Graph Neural Networks (GNNs), enabling the discovery of communities without prior knowledge. Compared to most existing sol…
Community DetectionGeoAI-Enhanced Community Detection on Spatial Networks with Graph Deep Learning
Spatial networks are useful for modeling geographic phenomena where spatial interaction plays an important role. To analyze the spatial networks and their internal structures, graph-based methods such as community detect…
AttributeCommunity DetectionDeep LearningGraph AttentionScalable Hypergraph Embedding System
Many problems such as node classification and link prediction in network data can be solved using graph embeddings. However, it is difficult to use graphs to capture non-binary relations such as communities of nodes. The…
Graph Embeddinghypergraph embeddingLink PredictionNode Classification