arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.09518cs.LGcs.NEstat.ML
收藏

基于记忆的图网络

Memory-Based Graph Networks

University of Toronto(多伦多大学);Vector Institute(向量研究所);Autodesk AI Lab(欧特克人工智能实验室);Sharif University of Technology(谢里夫理工大学)

Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris

摘要:

图神经网络(GNN)是一类深度模型,其对具有表示为图的任意拓扑的数据进行操作。我们为GNN引入了一个高效的内存层,可以联合学习节点表示并粗化图形。我们还介绍了基于这一层的两个新网络:基于记忆的GNN(MemGNN)和图形记忆网络(GMN),它们可以学习分层图形表示。实验结果表明,所提出的模型在九个图分类和回归基准测试中的八个中达到了最先进的结果。我们还表明,学习的表示可以对应于分子数据中的化学特征。代码和参考实现发布于:https://github.com/amirkhas/GraphMemoryNet

英文摘要:

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also introduce two new networks based on this layer: memory-based GNN (MemGNN) and graph memory network (GMN) that can learn hierarchical graph representations. The experimental results shows that the proposed models achieve state-of-the-art results in eight out of nine graph classification and regression benchmarks. We also show that the learned representations could correspond to chemical features in the molecule data. Code and reference implementations are released at: https://github.com/amirkhas/GraphMemoryNet

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑