rename FeaturedGraph to GNNGraph

Author: CarloLucibello

docs/make.jl

@@ -7,12 +7,12 @@ makedocs(;
     modules=[GraphNeuralNetworks],
     sitename = "GraphNeuralNetworks.jl",
     pages = ["Home" => "index.md",
-             "Graphs" => "graphs.md",
-             "Message passing" => "messagepassing.md",
-             "Building models" => "models.md",
+             "GNNGraph" => "gnngraph.md",
+             "Message Passing" => "messagepassing.md",
+             "Building Models" => "models.md",
              "API Reference" =>
                [
-                "Graphs" => "api/graphs.md",
+                "GNNGraph" => "api/gnngraph.md",
                 "Convolutional Layers" => "api/conv.md",
                 "Pooling Layers" => "api/pool.md",
                ],

docs/src/api/graphs.md renamed to docs/src/api/gnngraph.md

@@ -7,6 +7,6 @@ Pages   = ["api/graphs.md"]
 
 ```@autodocs
 Modules = [GraphNeuralNetworks]
-Pages   = ["featuredgraph.jl"]
+Pages   = ["gnngraph.jl"]
 Private = false
 ```

docs/src/graphs.md renamed to docs/src/gnngraph.md

@@ -23,16 +23,16 @@ function GNN(; nin, nhidden, nout)
         Dense(nhidden, nout))
 end
 
-function (net::GNN)(fg, x)
-    x = net.conv1(fg, x)
+function (net::GNN)(g, x)
+    x = net.conv1(g, x)
     x = dropout(x, 0.5)
-    x = net.conv2(fg, x)
+    x = net.conv2(g, x)
     x = net.dense(x)
     return x
 end
 
-function eval_loss_accuracy(X, y, ids, model, fg)
-    ŷ = model(fg, X)
+function eval_loss_accuracy(X, y, ids, model, g)
+    ŷ = model(g, X)
     l = logitcrossentropy(ŷ[:,ids], y[:,ids])
     acc = mean(onecold(ŷ[:,ids] |> cpu) .== onecold(y[:,ids] |> cpu))
     return (loss = round(l, digits=4), acc = round(acc*100, digits=2))
@@ -64,7 +64,7 @@ function train(; kws...)
     end
 
     data = Cora.dataset()
-    fg = FeaturedGraph(data.adjacency_list) |> device
+    g = GNNGraph(data.adjacency_list) |> device
     X = data.node_features |> device
     y = onehotbatch(data.node_labels, 1:data.num_classes) |> device
     train_ids = data.train_indices |> device
@@ -78,19 +78,19 @@ function train(; kws...)
     ps = Flux.params(model)
     opt = ADAM(args.η)
 
-    @info "NUM NODES: $(fg.num_nodes)  NUM EDGES: $(fg.num_edges)"
+    @info "NUM NODES: $(g.num_nodes)  NUM EDGES: $(g.num_edges)"
 
     function report(epoch)
-        train = eval_loss_accuracy(X, y, train_ids, model, fg)
-        test = eval_loss_accuracy(X, y, test_ids, model, fg)        
+        train = eval_loss_accuracy(X, y, train_ids, model, g)
+        test = eval_loss_accuracy(X, y, test_ids, model, g)        
         println("Epoch: $epoch   Train: $(train)   Test: $(test)")
     end
 
     ## TRAINING
     report(0)
     for epoch in 1:args.epochs
         gs = Flux.gradient(ps) do
-            ŷ = model(fg, X)
+            ŷ = model(g, X)
             logitcrossentropy(ŷ[:,train_ids], ytrain)
         end
 

examples/cora.jl

@@ -8,20 +8,20 @@ BenchmarkTools.ratio(x, ::Missing) = 0.0
 BenchmarkTools.ratio(::Missing, ::Missing) = missing
 
 function run_single_benchmark(N, c, D, CONV; gtype=:lg)
-    g = erdos_renyi(N, c / (N-1), seed=17)
+    data = erdos_renyi(N, c / (N-1), seed=17)
     X = randn(Float32, D, N)
 
-    fg = FeaturedGraph(g; nf=X, graph_type=gtype)
-    fg_gpu = fg |> gpu    
+    g = GNNGraph(data; nf=X, graph_type=gtype)
+    g_gpu = g |> gpu    
 
     m = CONV(D => D)
     m_gpu = m |> gpu
 
     res = Dict()
-    res["CPU"] = @benchmark $m($fg)
+    res["CPU"] = @benchmark $m($g)
 
     try [GCNConv, GraphConv, GATConv]
-        res["GPU"] = @benchmark CUDA.@sync($m_gpu($fg_gpu)) teardown=(GC.gc(); CUDA.reclaim())
+        res["GPU"] = @benchmark CUDA.@sync($m_gpu($g_gpu)) teardown=(GC.gc(); CUDA.reclaim())
     catch
         res["GPU"] = missing
     end

perf/perf.jl

@@ -16,8 +16,8 @@ using LightGraphs: AbstractGraph, outneighbors, inneighbors, is_directed, ne, nv
                   adjacency_matrix, degree
 
 export
-    # featured_graph
-    FeaturedGraph,
+    # gnngraph
+    GNNGraph,
     edge_index,
     node_feature, edge_feature, global_feature,
     adjacency_list, normalized_laplacian, scaled_laplacian,
@@ -56,7 +56,7 @@ export
     bypass_graph
 
 
-include("featuredgraph.jl")
+include("gnngraph.jl")
 include("graph_conversions.jl")
 include("utils.jl")