Graph Neural Networks: Theoretical Motivations

#Graph #Graph Neural Networks #Neural Networks #Machine Learning

We have changed the time!

We will discuss chapter 7 of Hamilton¹.

In this chapter, we will visit some of the theoretical underpinnings of graph neu- ral networks (GNNs). One of the most intriguing aspects of GNNs is that they were independently developed from distinct theoretical motivations.

We have changed the time of the event.

Hamilton2020 Hamilton WL. Graph representation learning. Synth lect artif intell mach learn. 2020;14: 1–159. doi:10.2200/s01045ed1v01y202009aim046 ↩︎

Planted: 2021-11-12 by NeuronStar;

: 2021-11-20T14:00:00 - 2021-11-20T15:30:00 (CET) : Lark（飞书） : More details on page Conditional Probability Estimation

References:

Hamilton2020 Hamilton WL. Graph representation learning. Synth lect artif intell mach learn. 2020;14: 1–159. doi:10.2200/s01045ed1v01y202009aim046

Current Ref:

cpe/25.gnn-2.md

Links from:

Graph Convolutional Matrix Completion

Multivariate Time-series Forecasting Using GNN

Multivariate Time-series Forecasting