[mlpack] GSoC Proposal: Graph Convolutional Networks (GCN)

[Ryan Curtin]

On Sun, Mar 15, 2020 at 11:21:48AM +0530, Hemal Mamtora wrote:
> Hello Mentors,
> 
> Thank you for your reviews regarding the project on the IRC. The've helped
> me shape the proposal well.

Hey there Hemal,

Glad to hear that things have been going well.  The basic idea of what
you wrote seems reasonable to me.  The use of arma::sp_mat to represent
graphs *should* be a reasonable approach, but it might be worth some
simple validation tests to make sure that arma::sp_mat is fast enough.
(Sometimes, a sparse representation of data can be slow.  However, I
think that arma::sp_mat *should* be fine... still, good to check.)

> *One query:*
> The Graph datasets available online have different formats like GraphML,
> Adjacency List in a CSV, Edge List in a CSV, etc.
> They would have to be converted to Adjacency Matrix.
> Most of the time the conversion is *straightforward* in O(E) time, where E
> is the number of edges.
> What are your views on having this functionality of ToAdjacencyMatrix() in
> MLpack.
> I think it should not be in MLpack. We could say that MLpack expects
> AdjacencyMatrix (Sparse or Dense) for Graph Networks.
> But if you think that this functionality should exist, I could start
> implementing it, asap.

Personally, I think that we could provide support in data::Load() to
load GraphML or adjacency lists or whatever sparse format, and I think
this could be useful to put into the mlpack codebase.  As it stands, I
think Armadillo supports loading coordinate list CSV files, so probably
a good bit of the support is already there.

Hope the input helps.

Thanks!

Ryan

-- 
Ryan Curtin    | "It's too bad she won't live!  But then again, who
ryan at ratml.org | does?" - Gaff