# FeaturedGraph Explanation

**URL:** <https://discourse.julialang.org/t/featuredgraph-explanation/66294>\
**Category:** Machine Learning\
**Created:** [August 12, 2021, 8:33pm UTC](https://discourse.julialang.org/t/featuredgraph-explanation/66294 "2021-08-12T20:33:34Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![NFSturm](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/nfsturm/32/26298_2.png) [@NFSturm](https://discourse.julialang.org/u/NFSturm)\
**Post date:** [August 12, 2021, 8:33pm UTC](https://discourse.julialang.org/t/featuredgraph-explanation/66294/1 "2021-08-12T20:33:34Z")

</div>

Dear Julia Community,

I was recently becoming interested in Machine Learning on graphs I found the `GeometricFlux` library that seems to be quite useful in that regard. My understanding of graphs in general is rather basic, but I still found that topic interesting. One feature that I cannot really wrap my head around is the `FeaturedGraph`.

I have a hard time understanding how to construct it. The documentation for is seems not to be specific about how to exactly construct a `FeaturedGraph`, particular how the _edge_ and _node features_ can be constructed using the type.

If there are N nodes, then one could maybe construct a N x K feature matrix with K features, but for the edges, I would need a multi-dimensional structure?

Sorry for the noob question 🙂