Graph Compression Networks
Graph Compression Networks
复制标题
DOI：
10.1109/bigdata52589.2021.9671652
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Ting Guo;Xingquan Zhu;Yang Wang;Fang Chen
中科院分区：
文献类型：
--
作者：
Ting Guo;Xingquan Zhu;Yang Wang;Fang Chen
图/网络在现实世界的应用中很常见，其中数据具有丰富的内容和复杂的关系。网络的日益普及也推动了许多网络学习算法的发展，如社区检测、聚类、分类和嵌入学习等。在现实中，大的网络体积往往隐藏了直接使用的学习算法的图。因此，希望具有将网络压缩到任意大小的灵活性，同时良好地保存网络拓扑和节点内容信息。在本文中，我们提出了一个图压缩网络（GEN），以实现网络压缩和嵌入在同一时间。我们的主题是利用网络拓扑来找到节点映射，这样密集连接的节点，包括它们的节点内容，被压缩为一个新的节点，学习一个潜在的向量（即嵌入）来表示压缩的节点。除了压缩学习之外，我们还开发了一种新的编码-解码框架，使用特征扩散过程来“扩展”凝聚网络。与传统的图卷积使用直接邻居消息传递不同，我们的解压缩提倡在压缩节点内传递高阶消息，以学习网络中所有节点的特征表示。GEN的一个独特优势是它利用图神经网络原理自动学习映射，因此可以将网络压缩到任意大小，并以最小的信息损失将其扩展到原始节点空间。实验和比较表明，GEN能够自动发现簇和社区，并将其压缩为新的节点。结果还表明，GEN实现了许多任务，包括图分类和节点聚类的性能提高。
Graphs/Networks are common in real-world applications where data have rich content and complex relationships. The increasing popularity also motivates many network learning algorithms, such as community detection, clustering, classification, and embedding learning, etc.. In reality, the large network volumes often hider a direct use of learning algorithms to the graphs. As a result, it is desirable to have the flexibility to condense a network to an arbitrary size, with well-preserved network topology and node content information. In this paper, we propose a graph compression network (GEN) to achieve network compression and embedding at the same time. Our theme is to leverage the network topology to find node mappings, such that densely connected nodes, including their node content, are compressed as a new node, with a latent vector (i.e. embedding) being learned to represent the compressed node. In addition to compression learning, we also develop a novel encoding-decoding framework, using feature diffusion process, to "decompress" the condensed network. Different from traditional graph convolution which uses direct-neighbor message passing, our decompression advocates high-order message passing within compressed nodes to learning feature representation for all nodes in the network. A unique strength of GEN is that it leverages the graph neural network principle to learn mapping automatically, so one can compress a network to an arbitrary size, and also decompress it to the original node space with minimum information loss. Experiments and comparisons confirm that GEN can automatically find clusters and communities, and compress them as new nodes. Results also show that GEN achieves improved performance for numerous tasks, including graph classification and node clustering.