Heterogeneous Graphs

Warning

Heterographs support is still experimental. The interface could be subject to change in the future.

Heterogeneus graphs (also called heterographs), are graphs where each node has a type, that we denote with symbols such as :user and :movie, and edges also represent different relations identified by a triple of symbols, (source_nodes, edge_type, target_nodes), as in (:user, :rate, :movie).

Different node/edge types can store different group of features and this makes heterographs a very flexible modeling tools and data containers.

In GraphNeuralNetworks.jl heterographs are implemented in the type GNNHeteroGraph.

GraphNeuralNetworks.GNNGraphs.GNNHeteroGraph — Type

GNNHeteroGraph(data; ndata, edata, gdata, num_nodes, graph_indicator, dir])

A type representing a heterogeneous graph structure. it is similar GNNGraph but node and edges are of different types.

Arguments

data: A dictionary or an iterable object that maps (sourcetype, edgetype, target_type) triples to (source, target) index vectors.
num_nodes: The number of nodes for each type. If not specified, inferred from g. Default nothing.
graph_indicator: For batched graphs, a dictionary of vectors containing the graph assignment of each node. Default nothing.
ndata: Node features. A dictionary of arrays or named tuple of arrays. The size of the last dimension of each array must be given by g.num_nodes.
edata: Edge features. A dictionary of arrays or named tuple of arrays. The size of the last dimension of each array must be given by g.num_edges.
gdata: Graph features. An array or named tuple of arrays whose last dimension has size num_graphs.

Warning

GNNHeteroGraph is still experimental and not fully supported. The interface could be subject to change in the future.

Examples

julia> using Flux, GraphNeuralNetworks

julia> num_nodes = Dict(:A => 10, :B => 20);

julia> edges1 = rand(1:num_nodes[:A], 20), rand(1:num_nodes[:B], 20)
([4, 8, 6, 3, 4, 7, 2, 7, 3, 2, 3, 4, 9, 4, 2, 9, 10, 1, 3, 9], [6, 4, 20, 8, 16, 7, 12, 16, 5, 4, 6, 20, 11, 19, 17, 9, 12, 2, 18, 12])

julia> edges2 = rand(1:num_nodes[:B], 30), rand(1:num_nodes[:A], 30)
([17, 5, 2, 4, 5, 3, 8, 7, 9, 7  …  19, 8, 20, 7, 16, 2, 9, 15, 8, 13], [1, 1, 3, 1, 1, 3, 2, 7, 4, 4  …  7, 10, 6, 3, 4, 9, 1, 5, 8, 5])

julia> eindex = ((:A, :rel1, :B) => edges1, (:B, :rel2, :A) => edges2);

julia> hg = GNNHeteroGraph(eindex; num_nodes)
GNNHeteroGraph:
  num_nodes: (:A => 10, :B => 20)
  num_edges: ((:A, :rel1, :B) => 20, (:B, :rel2, :A) => 30)

julia> hg.num_edges
Dict{Tuple{Symbol, Symbol, Symbol}, Int64} with 2 entries:
(:A, :rel1, :B) => 20
(:B, :rel2, :A) => 30

# Let's add some node features
julia> ndata = Dict(:A => (x = rand(2, num_nodes[:A]), y = rand(3, num_nodes[:A])),
                    :B => rand(10, num_nodes[:B]));

julia> hg = GNNHeteroGraph(eindex; num_nodes, ndata)
GNNHeteroGraph:
    num_nodes: (:A => 10, :B => 20)
    num_edges: ((:A, :rel1, :B) => 20, (:B, :rel2, :A) => 30)
    ndata:
    :A  =>  (x = 2×10 Matrix{Float64}, y = 3×10 Matrix{Float64})
    :B  =>  x = 10×20 Matrix{Float64}

# Access features of nodes of type :A
julia> hg.ndata[:A].x
2×10 Matrix{Float64}:
    0.825882  0.0797502  0.245813  0.142281  0.231253  0.685025  0.821457  0.888838  0.571347   0.53165
    0.631286  0.316292   0.705325  0.239211  0.533007  0.249233  0.473736  0.595475  0.0623298  0.159307

See also GNNGraph for a homogeneous graph type. and rand_heterograph for a function to generate random heterographs.

source

Missing docstring.

Missing docstring for rand_heterograph. Check Documenter's build log for details.