Update documentation for convolutions on TemporalSnapshotsGNNGraphs (#379)

* Update table add GINConv

* Add example in the docs

* Fix spaces and name

Co-authored-by: Carlo Lucibello <[email protected]>

* Fix other spaces

---------

Co-authored-by: Carlo Lucibello <[email protected]>

Author: aurorarossi

docs/src/api/conv.md

@@ -13,27 +13,28 @@ The table below lists all graph convolutional layers implemented in the *GraphNe
 - *Edge Weight*: supports scalar weights (or equivalently scalar features) on edges. 
 - *Edge Features*: supports feature vectors on edges.
 - *Heterograph*: supports heterogeneous graphs (see [`GNNHeteroGraph`](@ref)).
+- *TemporalSnapshotsGNNGraphs*: supports temporal graphs (see [`TemporalSnapshotsGNNGraph`](@ref)) by applying the convolution layers to each snapshot independently.
 
-| Layer                       |Sparse Ops|Edge Weight|Edge Features| Heterograph  |
-| :--------                   |  :---:   |:---:      |:---:        |  :---:       |
-| [`AGNNConv`](@ref)          |          |           |     ✓       |              | 
-| [`CGConv`](@ref)            |          |           |     ✓       |              |
-| [`ChebConv`](@ref)          |          |           |             |              |
-| [`EGNNConv`](@ref)          |          |           |     ✓       |              |
-| [`EdgeConv`](@ref)          |          |           |             |              |
-| [`GATConv`](@ref)           |          |           |     ✓       |              |
-| [`GATv2Conv`](@ref)         |          |           |     ✓       |              |
-| [`GatedGraphConv`](@ref)    |     ✓    |           |             |              |
-| [`GCNConv`](@ref)           |     ✓    |     ✓     |             |              | 
-| [`GINConv`](@ref)           |     ✓    |           |             |              |
-| [`GMMConv`](@ref)           |          |           |     ✓       |              |
-| [`GraphConv`](@ref)         |     ✓    |           |             |       ✓      |
-| [`MEGNetConv`](@ref)        |          |           |     ✓       |              |
-| [`NNConv`](@ref)            |          |           |     ✓       |              |
-| [`ResGatedGraphConv`](@ref) |          |           |             |              |
-| [`SAGEConv`](@ref)          |     ✓    |           |             |              |
-| [`SGConv`](@ref)            |     ✓    |           |             |              |
-| [`TransformerConv`](@ref)   |          |           |     ✓       |              |
+| Layer                       |Sparse Ops|Edge Weight|Edge Features| Heterograph  | TemporalSnapshotsGNNGraphs |
+| :--------                   |  :---:   |:---:      |:---:        |  :---:       | :---:                      |
+| [`AGNNConv`](@ref)          |          |           |     ✓       |              |                    |                          
+| [`CGConv`](@ref)            |          |           |     ✓       |              |                           | 
+| [`ChebConv`](@ref)          |          |           |             |              |                            |
+| [`EGNNConv`](@ref)          |          |           |     ✓       |              |                           |
+| [`EdgeConv`](@ref)          |          |           |             |              |                            |  
+| [`GATConv`](@ref)           |          |           |     ✓       |              |                            |
+| [`GATv2Conv`](@ref)         |          |           |     ✓       |              |                            |
+| [`GatedGraphConv`](@ref)    |     ✓    |           |             |              |                            |
+| [`GCNConv`](@ref)           |     ✓    |     ✓     |             |              |                            |
+| [`GINConv`](@ref)           |     ✓    |           |             |              |                ✓           |
+| [`GMMConv`](@ref)           |          |           |     ✓       |              |                            |
+| [`GraphConv`](@ref)         |     ✓    |           |             |       ✓      |                            |   
+| [`MEGNetConv`](@ref)        |          |           |     ✓       |              |                            |              
+| [`NNConv`](@ref)            |          |           |     ✓       |              |                            |
+| [`ResGatedGraphConv`](@ref) |          |           |             |              |                            |
+| [`SAGEConv`](@ref)          |     ✓    |           |             |              |                           |
+| [`SGConv`](@ref)            |     ✓    |           |             |              |                           |
+| [`TransformerConv`](@ref)   |          |           |     ✓       |              |                           |
 
 
 ## Docs

docs/src/temporalgraph.md

@@ -121,3 +121,23 @@ julia> tg.ndata # vector of Datastore for node features
 julia> typeof(tg.ndata.x) # vector containing the x feature of each snapshot
 Vector{Matrix{Float64}}
 ```
+
+## Graph convolutions on TemporalSnapshotsGNNGraph
+
+A graph convolutional layer can be applied to each snapshot independently, in the next example we apply a `GINConv` layer to each snapshot of a `TemporalSnapshotsGNNGraph`. The list of compatible graph convolution layers can be found [here](api/conv.md). 
+
+```jldoctest
+julia> using GraphNeuralNetworks, Flux
+
+julia> snapshots = [rand_graph(10, 20; ndata = rand(3, 10)), rand_graph(10, 14; ndata = rand(3, 10))];
+
+julia> tg = TemporalSnapshotsGNNGraph(snapshots);
+
+julia> m = GINConv(Dense(3 => 1), 0.4);
+
+julia> output = m(tg, tg.ndata.x);
+
+julia> size(output[1])
+(1, 10)
+```
+