返回
A Normalizing Flow-Based Co-Embedding Model for Attributed Networks
DOI:10.1145/3477049.png)
摘要
En 中文
Network embedding is a technique that aims at inferring the low-dimensional representations of nodes in a semantic space. In this article, we study the problem of inferring the low-dimensional representations of both nodes and attributes for attributed networks in the same semantic space such that the affinity between a node and an attribute can be effectively measured. Intuitively, this problem can be addressed by simply utilizing existing variational auto-encoder (VAE) based network embedding algorithms. However, the variational posterior distribution in previous VAE based network embedding algorithms is often assumed and restricted to be a mean-field Gaussian distribution or other simple distribution families, which results in poor inference of the embeddings. To alleviate the above defect, we propose a novel VAE-based co-embedding method for attributed network, F-CAN, where posterior distributions are flexible, complex, and scalable distributions constructed through the normalizing flow. We evaluate our proposed models on a number of network tasks with several benchmark datasets. Experimental results demonstrate that there are clear improvements in the qualities of embeddings generated by our model to the state-of-the-art attributed network embedding methods.
Keyword:
Attributed network
embedding
variational auto-encoder
normalizing flow
期刊
IF:
4.8
论文数:
1.3K
被引数:
5.5K
机构
引用论文
Plant trait-mediated interactions between early and late herbivores on common figwort (Scrophularia nodosa) and effects on plant seed set早期和晚期植食性昆虫通过植物性状介导的相互作用对普通玄参 (Scrophularia nodosa) 的种子结实率的影响
Écoscience
IF0
High-elevation fire regimes in subalpine ribbon forests during the Little Ice Age and Medieval Period along the Continental Divide, Colorado, U.S.A.美国科罗拉多州大陆分水岭亚高山带状林在高海拔地区的火灾格局:小冰期和中世纪时期的研究

