Inspired by recent success of graph contrastive learning methods, we propose a self-supervised framework for Graph Neural Networks (GNNs) named Adaptive Multi-layer Contrastive (AMC-GNN). Specifically, AMC-GNN generates different views through data augmentation and compares the output embeddings at layers neural network encoders to obtain feature representations downstream tasks. Meanwhile, lea...

The sewer layout in flat areas significantly influences the construction and operational costs as well as reliability of the network performance. To find an optimum design of sewer networks for flat areas, this study presents a multi-objective optimization problem with the objective functions of 1- the cost and 2- the reliability. The reliability criterion is defined as the effect of a clogging...

A new formulation of adaptive categorization game of ART-type networks is described in this papet Learning automata dynamics is introduced into adaptive categorization game in ART-type networks so that the vigilance parameters p are adjusted to give variable sized clusters. Moreovel; repeated game analysis is also conducted on the learning automata based adaptive categorization game to study th...