Deep Learning and Spectral Embedding for Graph Partitioning
원문 초록
We present a graph bisection and partitioning algorithm based on graph neural networks. For each node in the graph, the network outputs probabilities for each of the partitions. The graph neural network consists of two modules: an embedding phase and a partitioning phase. The embedding phase is trained first by minimizing a loss function inspired by spectral graph theory. The partitioning module is trained through a loss function that corresponds to the expected value of the normalized cut. Both parts of the neural network rely on SAGE convolutional layers and graph coarsening using heavy edge matching. The multilevel structure of the neural network is inspired by the multigrid algorithm. Our approach generalizes very well to bigger graphs and has partition quality comparable to METIS, Scotch and spectral partitioning, with shorter runtime compared to METIS and spectral partitioning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Node-level Contrastive Unlearning on Graph Neural Networks
Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation
PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training
Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs
RLHGNN: Reinforcement Learning-driven Heterogeneous Graph Neural Network for Next Activity Prediction in Business Processes
토론
이 논문과 연결된 포럼 글이 아직 없습니다.