Recently, maximizing mutual information has emerged as a powerful method for unsupervised graph representation learning. The existing methods are typically effective to capture information from the topology view but ignore the feature view. To circumvent this issue, we propose a novel approach by exploiting mutual information maximization across feature and topology views. Specifically, we first utilize a multi-view representation learning module to better capture both local and global information content across feature and topology views on graphs. To model the information shared by the feature and topology spaces, we then develop a common representation learning module using mutual information maximization and reconstruction loss minimization. To explicitly encourage diversity between graph representations from the same view, we also introduce a disagreement regularization to enlarge the distance between representations from the same view. Experiments on synthetic and real-world datasets demonstrate the effectiveness of integrating feature and topology views. In particular, compared with the previous supervised methods, our proposed method can achieve comparable or even better performance under the unsupervised representation and linear evaluation protocol.

With virtualized environments performance issues can be hard to pinpoint. IT departments can find it difficult to spot whether the cause is in the application, network, storage, or virtualization layer of the infrastructure. Software optimization specialist SIOS is bringing machine learning to bear on this problem with the latest release of SIOS iQ, its analytics software for VM environments. For the first time, IT staff can easily identify and resolve the root causes of performance issues based on analysis of both the VMware infrastructure and the SQL Server application environment. Other advances enable users to accurately predict and forecast performance and capacity utilization, improve efficiency by identifying and resizing under- and over-provisioned VMs, and save datastore capacity by instantly identifying rogue disk files (VMDKs).