Merge pull request #1 from CarloLucibello/cl/nullgraph

layers do not store graphs internally

Author: CarloLucibello

.github/workflows/CI.yml

@@ -1,7 +1,12 @@
 name: CI
 on:
-  - push
-  - pull_request
+  pull_request:
+    branches:
+      - master
+  push:
+    branches:
+      - master
+    tags: '*'
 jobs:
   test:
     name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }}
@@ -10,7 +15,8 @@ jobs:
       fail-fast: false
       matrix:
         version:
-          - '1.6'
+          - '1.6' # Replace this with the minimum Julia version that your package supports. E.g. if your package requires Julia 1.5 or higher, change this to '1.5'.
+          - '1' # Leave this line unchanged. '1' will automatically expand to the latest stable 1.x release of Julia.
           - 'nightly'
         os:
           - ubuntu-latest
@@ -37,28 +43,5 @@ jobs:
       - uses: julia-actions/julia-processcoverage@v1
       - uses: codecov/codecov-action@v1
         with:
+          # token: ${{ secrets.CODECOV_TOKEN }}
           file: lcov.info
-  docs:
-    name: Documentation
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - uses: julia-actions/setup-julia@v1
-        with:
-          version: '1'
-      - run: |
-          julia --project=docs -e '
-            using Pkg
-            Pkg.develop(PackageSpec(path=pwd()))
-            Pkg.instantiate()'
-      - run: |
-          julia --project=docs -e '
-            using Documenter: DocMeta, doctest
-            using GraphNeuralNetworks
-            DocMeta.setdocmeta!(GraphNeuralNetworks, :DocTestSetup, :(using GraphNeuralNetworks); recursive=true)
-            doctest(GraphNeuralNetworks)'
-      - run: julia --project=docs docs/make.jl
-        env:
-          JULIA_PKG_SERVER: ""
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          DOCUMENTER_KEY: ${{ secrets.DOCUMENTER_KEY }}

.github/workflows/docs.yml

@@ -0,0 +1,24 @@
+name: Documentation
+
+on:
+  push:
+    branches:
+      - master
+    tags: '*'
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: julia-actions/setup-julia@latest
+        with:
+          version: '1.6'
+      - name: Install dependencies
+        run: julia --project=docs/ -e 'using Pkg; Pkg.develop(PackageSpec(path=pwd())); Pkg.instantiate()'
+      - name: Build and deploy
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # If authenticating with GitHub Actions token
+          DOCUMENTER_KEY: ${{ secrets.DOCUMENTER_KEY }} # If authenticating with SSH deploy key
+        run: julia --project=docs/ docs/make.jl

.gitignore

@@ -1,5 +1,5 @@
 *.jl.*.cov
 *.jl.cov
 *.jl.mem
-/Manifest.toml
+Manifest.toml
 /docs/build/

README.md

@@ -1,31 +1,29 @@
 # GraphNeuralNetworks.jl
 
-[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://fluxml.ai/GraphNeuralNetworks.jl/stable)
-[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://fluxml.ai/GraphNeuralNetworks.jl/dev)
+[![](https://img.shields.io/badge/docs-stable-blue.svg)](https://CarloLucibello.github.io/GraphNeuralNetworks.jl/stable)
+[![](https://img.shields.io/badge/docs-dev-blue.svg)](https://CarloLucibello.github.io/GraphNeuralNetworks.jl/dev)
 ![](https://github.com/CarloLucibello/GraphNeuralNetworks.jl/actions/workflows/ci.yml/badge.svg)
 [![codecov](https://codecov.io/gh/FluxML/GraphNeuralNetworks.jl/branch/master/graph/badge.svg)](https://codecov.io/gh/CarloLucibello/GraphNeuralNetworks.jl)
 
-GraphNeuralNetworks is a geometric deep learning library for [Flux](https://github.com/FluxML/Flux.jl). This library aims to be compatible with packages from [JuliaGraphs](https://github.com/JuliaGraphs) ecosystem and have support of CUDA GPU acceleration with [CUDA](https://github.com/JuliaGPU/CUDA.jl). Message passing scheme is implemented as a flexbile framework and fused with Graph Network block scheme. GraphNeuralNetworks is compatible with other packages that are composable with Flux.
+*GraphNeuralNetworks* is a graph neural network library for Julia based on the [Flux.jl](https://github.com/FluxML/Flux.jl) deep learning framework.
 
-Suggestions, issues and pull requsts are welcome.
+Some of its noticeable features are the following:
+
+* Based on the Flux deep learning framework.
+* CUDA support.
+* Integrated with the JuliaGraphs ecosystem.
+* Supports generic graph neural network architectures.
+* Easy to define custom graph convolutional layers.
 
 ## Installation
 
 ```julia
 ]add GraphNeuralNetworks
 ```
 
-## Features
-
-* Extend Flux deep learning framework in Julia and compatible with Flux layers.
-* Support of CUDA GPU with CUDA.jl
-* Integrate with existing JuliaGraphs ecosystem
-* Support generic graph neural network architectures
-* Variable graph inputs are supported. You use it when diverse graph structures are prepared as inputs to the same model.
-
 ## Featured Graphs
 
-GraphNeuralNetworks handles graph data (the topology plus node/vertex/graph features)
+GraphNeuralNetworks handles graph data (the graph topology + node/edge/global features)
 thanks to the type `FeaturedGraph`.
 
 A `FeaturedGraph` can be constructed out of 
@@ -34,26 +32,45 @@ adjacency matrices, adjacency lists, LightGraphs' types...
 ```julia
 fg = FeaturedGraph(adj_list)   
 ```
+
 ## Graph convolutional layers
 
 Construct a GCN layer:
 
 ```julia
-GCNConv([fg,] input_dim => output_dim, relu)
+GCNConv(input_dim => output_dim, relu)
 ```
 
-## Use it as you use Flux
+## Usage Example
 
 ```julia
-model = Chain(GCNConv(fg, 1024 => 512, relu),
-              Dropout(0.5),
-              GCNConv(fg, 512 => 128),
-              Dense(128, 10))
-## Loss
-loss(x, y) = logitcrossentropy(model(x), y)
-accuracy(x, y) = mean(onecold(model(x)) .== onecold(y))
-
-## Training
+struct GNN
+    conv1
+    conv2 
+    dense
+end
+
+@functor GNN
+
+function GNN()
+    GNN(GCNConv(1024=>512, relu),
+        GCNConv(512=>128, relu), 
+        Dense(128, 10))
+end
+
+function (net::GNN)(g, x)
+    x = net.conv1(g, x)
+    x = dropout(x, 0.5)
+    x = net.conv2(g, x)
+    x = net.dense(x)
+    return x
+end
+
+model = GNN()
+
+loss(x, y) = logitcrossentropy(model(fg, x), y)
+accuracy(x, y) = mean(onecold(model(fg, x)) .== onecold(y))
+
 ps = Flux.params(model)
 train_data = [(train_X, train_y)]
 opt = ADAM(0.01)

docs/Manifest.toml

@@ -1,3 +1,3 @@
 [deps]
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
-GraphNeuralNetworks = "b59e9cf9-92e9-4253-8889-0456869b82e0"
+GraphNeuralNetworks = "cffab07f-9bc2-4db1-8861-388f63bf7694"

docs/Project.toml

@@ -5,19 +5,10 @@ DocMeta.setdocmeta!(GraphNeuralNetworks, :DocTestSetup, :(using GraphNeuralNetwo
 
 makedocs(;
     modules=[GraphNeuralNetworks],
-    authors="Carlo Lucibello <[email protected]> and contributors",
-    repo="https://github.com/CarloLucibello/GraphNeuralNetworks.jl/blob/{commit}{path}#{line}",
-    sitename="GraphNeuralNetworks.jl",
-    format=Documenter.HTML(;
-        prettyurls=get(ENV, "CI", "false") == "true",
-        canonical="https://CarloLucibello.github.io/GraphNeuralNetworks.jl",
-        assets=String[],
-    ),
+    sitename = "GraphNeuralNetworks.jl",
     pages=[
         "Home" => "index.md",
     ],
 )
 
-deploydocs(;
-    repo="github.com/CarloLucibello/GraphNeuralNetworks.jl",
-)
+deploydocs(repo="github.com/CarloLucibello/GraphNeuralNetworks.jl.git")

docs/make.jl

@@ -64,7 +64,6 @@ include("layers/msgpass.jl")
 
 include("layers/conv.jl")
 include("layers/pool.jl")
-include("models.jl")
 include("layers/misc.jl")
 
 

src/GraphNeuralNetworks.jl

@@ -5,16 +5,7 @@ https://juliagraphs.org/LightGraphs.jl/latest/types/#AbstractGraph-Type
 https://juliagraphs.org/LightGraphs.jl/latest/developing/#Developing-Alternate-Graph-Types
 =============================================#
 
-abstract type AbstractFeaturedGraph <: AbstractGraph{Int} end
-
-"""
-    NullGraph()
-
-Null object for `FeaturedGraph`.
-"""
-struct NullGraph <: AbstractFeaturedGraph end
-
-const COO_T = Tuple{T, T, V} where {T <: AbstractVector,V}
+const COO_T = Tuple{T, T, V} where {T <: AbstractVector, V}
 const ADJLIST_T = AbstractVector{T} where T <: AbstractVector
 const ADJMAT_T = AbstractMatrix
 const SPARSE_T = AbstractSparseMatrix # subset of ADJMAT_T
@@ -93,7 +84,7 @@ source, target = edge_index(fg)
 
 See also [`graph`](@ref), [`edge_index`](@ref), [`node_feature`](@ref), [`edge_feature`](@ref), and [`global_feature`](@ref) 
 """
-struct FeaturedGraph{T<:Union{COO_T,ADJMAT_T}} <: AbstractFeaturedGraph
+struct FeaturedGraph{T<:Union{COO_T,ADJMAT_T}}
     graph::T
     num_nodes::Int
     num_edges::Int