The era of “data deluge” has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and …
T Prouteau, V Connes, N Dugué, A Perez… - … on Intelligent Data …, 2021 - Springer
While graph embedding aims at learning low-dimensional representations of nodes encompassing the graph topology, word embedding focus on learning word vectors that …
Motivation Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins and drugs) and edges represent relational ties …
L Yu, L Sun, B Du, C Liu, W Lv, H Xiong - arXiv preprint arXiv:2012.14722, 2020 - arxiv.org
Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of multiple types of nodes and edges. Representation learning on heterogeneous graphs aims …
Unsupervised graph-level representation learning has recently shown great potential in a variety of domains, ranging from bioinformatics to social networks. Plenty of graph …
In classical graph signal processing (GSP), the underlying topological structures are restricted in terms of dimensionality. A graph or a 1-complex is a combinatorial object that …
Y Li, C Meng, C Shahabi, Y Liu - ICML Workshop on Learning …, 2019 - liyaguang.github.io
A variety of real-world applications require the modeling and the simulation of dynamical systems, eg, physics, transportation and climate. With the increase of complexity, it becomes …
Z Huang, Y Sun, W Wang - Proceedings of the 27th ACM SIGKDD …, 2021 - dl.acm.org
Many real-world systems such as social networks and moving planets are dynamic in nature, where a set of coupled objects are connected via the interaction graph and exhibit …
Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational …