123 papers with code • 1 benchmarks • 4 datasets
The goal of Graph Representation Learning is to construct a set of features (‘embeddings’) representing the structure of the graph and the data thereon. We can distinguish among Node-wise embeddings, representing each node of the graph, Edge-wise embeddings, representing each edge in the graph, and Graph-wise embeddings representing the graph as a whole.
Unfortunately, the lack of large-scale terminology definition dataset hinders the process toward definition generation.
In a different GRL approach, spectral methods based on graph filtering have emerged addressing over smoothing; however, up to now, they employ traditional neural networks that cannot efficiently exploit the structure of graph data.
Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike.
A few KGE techniques address interpretability, i. e., mapping the connectivity patterns of the relations (i. e., symmetric/asymmetric, inverse, and composition) to a geometric interpretation such as rotations.
The fundamental problem with these studies is that they ignore the evolution of services over time and the representation gap between services and requirements.
In this paper, we propose a novel class of spectral graph convolutional networks that implement graph convolutions with adaptive graph wavelets.