IEEE

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

Abstract: Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series ...
GitHub

Convolutional 2D Knowledge Graph Embeddings resources.

ConvE with 8 times less parameters is still more powerful than DistMult. Relational Graph Convolutional Networks use roughly 32x more parameters to have the same performance as ConvE.
GitHub

Ligra: A Lightweight Graph Processing Framework for Shared Memory

The code for Ligra, Ligra+, and Hygra is located in the ligra/ directory. The code for the applications is in the apps/ directory, which is where compilation should be performed. Example inputs are ...
IEEE

A Multi-Dimensional Graph Convolution Network for EEG Emotion Recognition

Abstract: Due to the changeable, high-dimensional, nonstationary, and other characteristics of electroencephalography (EEG) signals, the recognition of EEG signals is mostly limited to independent ...