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...

In this paper, we extend the bilinear generalized approximate message passing (BiG-AMP) approach, originally proposed for high-dimensional regression, to multi-layer case handling of cascaded problem such as matrix-factorization arising in relay communication among others. Assuming statistically independent matrix entries with known priors, new algorithm called ML-BiGAMP could general sum-produ...

In this study, we propose a multi-layer perceptron with a glial network which is inspired from the features of glias in the brain. All glias in the proposed network generate independent oscillations, and the oscillations propagate through the glial network with attenuation. We apply the proposed network to the two-spiral problem. Computer simulations show that the proposed network gains a bette...

We develop a multi-length scale (multi-fractal) theory for the effect of rock heterogeneity on the growth of the mixing layer of the flow of a passive tracer through porous media. The multi-fractal exponent of the size of the mixing layer is determined analytically from the statistical properties of a random velocity (permeability) field. The anomalous diffusion of the mixing layer can occur bo...

In the present study, vibration of cylindrical laminates with different layers and angles were studied. In order to actuate and polarize in radial direction, a piezoelectric layer was located at outer surface of composite shell. Laminates were assumed long enough so that plane strain state analysis in 2D can be used properly. In order to satisfy the boundary conditions, variables in terms of Fo...