IEEE

Self-Supervised Masked Graph Autoencoder for Hyperspectral Anomaly Detection

Abstract: Hyperspectral image anomaly detection faces the challenge of difficulty in annotating anomalous targets. Autoencoder(AE)-based methods are widely used due to their excellent image ...
IEEE

Dual Mutual Information-Driven Multimodal Recommendation with Denoising Graph Autoencoder

Abstract: Recently, multimodal recommendation (MMRec) has received much attention, which models user preferences based on both user behaviors and modality information. Although current graph neural ...
BIOENGINEER

AI Learns to Spot Failing EV Batteries Before They Catch Fire

Researchers have developed an unsupervised deep learning model called GSA-VAE that detects faults in electric vehicle ...
BIOENGINEER

Dual autoencoder framework sharpens single-cell clustering accuracy

A new deep clustering method, scDAEC, combines two autoencoders and multi-head attention to untangle noisy single-cell RNA ...
GitHub

brepvgae_variational_graph_autoencoder_with_unified_latent_representation_for_b-.md

BrepVGAE unifies heterogeneous "faces" and "edges" in CAD B-rep models as nodes of a single sparse isomorphic graph. Using a Variational Graph Autoencoder (VGAE), it compresses the graph into a global ...
GitHub

Graph-Convolutional Autoencoder for Steady Aerodynamic Vector Fields Prediction

This code implements a deep graph-convolutional autoencoder for predicting steady aerodynamic surface distributions of pressure (CP) and skin-friction (CFx, CFy, CFz) over a 3D wing. It includes: ...
Europe PMC

spaMGCN: a graph convolutional network with autoencoder for spatial domain identification using multi-scale adaptation.

Spatial domain identification is crucial in spatial transcriptomics analysis. Existing methods excel with continuous and clustered distributions but struggle with discrete ones. We present spaMGCN, an ...