Start inference GLMSBM

Author: gdalle

Manifest.toml

@@ -1,8 +1,8 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.9.2"
+julia_version = "1.10.0-beta2"
 manifest_format = "2.0"
-project_hash = "dd3777d035d7f906717e2a66a2e6f5c3854a6b1a"
+project_hash = "4013fd98503838d81ad2bc81b622895c0637888e"
 
 [[deps.ArgTools]]
 uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
@@ -33,7 +33,7 @@ weakdeps = ["Dates", "LinearAlgebra"]
 [[deps.CompilerSupportLibraries_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
-version = "1.0.5+0"
+version = "1.0.5+1"
 
 [[deps.DataStructures]]
 deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
@@ -45,6 +45,12 @@ version = "0.18.14"
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
 
+[[deps.DensityInterface]]
+deps = ["InverseFunctions", "Test"]
+git-tree-sha1 = "80c3e8639e3353e5d2912fb3a1916b8455e2494b"
+uuid = "b429d917-457f-4dbc-8f4c-0cc954292b1d"
+version = "0.4.0"
+
 [[deps.Distributed]]
 deps = ["Random", "Serialization", "Sockets"]
 uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
@@ -72,15 +78,21 @@ version = "0.1.3"
 deps = ["Markdown"]
 uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 
+[[deps.InverseFunctions]]
+deps = ["Test"]
+git-tree-sha1 = "68772f49f54b479fa88ace904f6127f0a3bb2e46"
+uuid = "3587e190-3f89-42d0-90ee-14403ec27112"
+version = "0.1.12"
+
 [[deps.LibCURL]]
 deps = ["LibCURL_jll", "MozillaCACerts_jll"]
 uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
-version = "0.6.3"
+version = "0.6.4"
 
 [[deps.LibCURL_jll]]
 deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
 uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
-version = "7.84.0+0"
+version = "8.0.1+1"
 
 [[deps.LibGit2]]
 deps = ["Base64", "NetworkOptions", "Printf", "SHA"]
@@ -89,7 +101,7 @@ uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
 [[deps.LibSSH2_jll]]
 deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
 uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8"
-version = "1.10.2+0"
+version = "1.11.0+1"
 
 [[deps.Libdl]]
 uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
@@ -114,14 +126,14 @@ uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 [[deps.MbedTLS_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
-version = "2.28.2+0"
+version = "2.28.2+1"
 
 [[deps.Mmap]]
 uuid = "a63ad114-7e13-5084-954f-fe012c677804"
 
 [[deps.MozillaCACerts_jll]]
 uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
-version = "2022.10.11"
+version = "2023.1.10"
 
 [[deps.NetworkOptions]]
 uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
@@ -130,7 +142,7 @@ version = "1.2.0"
 [[deps.OpenBLAS_jll]]
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
 uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
-version = "0.3.21+4"
+version = "0.3.23+2"
 
 [[deps.OrderedCollections]]
 git-tree-sha1 = "d321bf2de576bf25ec4d3e4360faca399afca282"
@@ -140,7 +152,7 @@ version = "1.6.0"
 [[deps.Pkg]]
 deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "Serialization", "TOML", "Tar", "UUIDs", "p7zip_jll"]
 uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
-version = "1.9.2"
+version = "1.10.0"
 
 [[deps.PrecompileTools]]
 deps = ["Preferences"]
@@ -169,7 +181,7 @@ deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
 uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
 
 [[deps.Random]]
-deps = ["SHA", "Serialization"]
+deps = ["SHA"]
 uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 
 [[deps.SHA]]
@@ -201,6 +213,7 @@ uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
 [[deps.SparseArrays]]
 deps = ["Libdl", "LinearAlgebra", "Random", "Serialization", "SuiteSparse_jll"]
 uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
+version = "1.10.0"
 
 [[deps.StaticArrays]]
 deps = ["LinearAlgebra", "Random", "StaticArraysCore"]
@@ -225,7 +238,7 @@ version = "1.9.0"
 [[deps.SuiteSparse_jll]]
 deps = ["Artifacts", "Libdl", "Pkg", "libblastrampoline_jll"]
 uuid = "bea87d4a-7f5b-5778-9afe-8cc45184846c"
-version = "5.10.1+6"
+version = "7.2.0+1"
 
 [[deps.TOML]]
 deps = ["Dates"]
@@ -237,6 +250,10 @@ deps = ["ArgTools", "SHA"]
 uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
 version = "1.10.0"
 
+[[deps.Test]]
+deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
+uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
 [[deps.UUIDs]]
 deps = ["Random", "SHA"]
 uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
@@ -247,19 +264,19 @@ uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
 [[deps.Zlib_jll]]
 deps = ["Libdl"]
 uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
-version = "1.2.13+0"
+version = "1.2.13+1"
 
 [[deps.libblastrampoline_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
-version = "5.8.0+0"
+version = "5.8.0+1"
 
 [[deps.nghttp2_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
-version = "1.48.0+0"
+version = "1.52.0+1"
 
 [[deps.p7zip_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
-version = "17.4.0+0"
+version = "17.4.0+2"

Project.toml

@@ -4,6 +4,7 @@ authors = ["Guillaume Dalle <22795598+gdalle@users.noreply.github.com> and contr
 version = "0.1.0"
 
 [deps]
+DensityInterface = "b429d917-457f-4dbc-8f4c-0cc954292b1d"
 Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 PrecompileTools = "aea7be01-6a6a-4083-8856-8a6e6704d82a"

docs/plots.jl

@@ -16,7 +16,7 @@ function compute_fig1(; N=3 * 10^3, P=N ÷ 10, d=5, μ=2, ρ=0.1, λ_values=0:0.
     @threads for i in 1:trials
         for j in eachindex(λ_values)
             λ = λ_values[j]
-            csbm = ContextualSBM(; N, P, d, μ, λ, ρ)
+            csbm = CSBM(; N, P, d, μ, λ, ρ)
             (; qᵤ, qᵥ) = evaluate_amp(rng; csbm)
             qᵤ_values[i, j] = qᵤ
             qᵥ_values[i, j] = qᵥ

src/StochasticBlockModelVariants.jl

@@ -1,5 +1,6 @@
 module StochasticBlockModelVariants
 
+using DensityInterface: logdensityof, densityof
 using Graphs: AbstractGraph, neighbors
 using LinearAlgebra: dot, mul!, norm
 using PrecompileTools: @compile_workload
@@ -9,21 +10,23 @@ using SimpleWeightedGraphs: SimpleWeightedGraph
 using Statistics: mean, std
 using SparseArrays: SparseMatrixCSC, sparse, findnz
 
-export ContextualSBM, ContextualSBMLatents, ContextualSBMObservations
-export affinities, effective_snr
+export nb_features, average_degree, communities_snr, affinities, features_snr, effective_snr
+export CSBM, LatentsCSBM, ObservationsCSBM
+export GLMSBM, LatentsGLMSBM, ObservationsGLMSBM
 export overlaps
 export init_amp, update_amp!, run_amp, evaluate_amp
 
 include("abstract_sbm.jl")
 include("utils.jl")
 include("csbm.jl")
+include("glmsbm.jl")
 include("csbm_inference.jl")
 
-@compile_workload begin
-    rng = default_rng()
-    csbm = ContextualSBM(; N=10^2, P=10^2, d=5, λ=2, μ=2, ρ=0.1)
-    (; observations) = rand(rng, csbm)
-    run_amp(rng; observations, csbm, max_iterations=2)
-end
+# @compile_workload begin
+#     rng = default_rng()
+#     csbm = CSBM(; N=10^2, P=10^2, d=5, λ=2, μ=2, ρ=0.1)
+#     (; observations) = rand(rng, csbm)
+#     run_amp(rng; observations, csbm, max_iterations=2)
+# end
 
 end

src/abstract_sbm.jl

@@ -5,6 +5,20 @@ Abstract supertype for Stochastic Block Models with additional node features.
 """
 abstract type AbstractSBM end
 
+"""
+    length(sbm)
+
+Return the number of nodes `N` in the graph.
+"""
+Base.length
+
+"""
+    nb_features(sbm)
+
+Return the number of features for each node in the graph.
+"""
+function nb_features end
+
 """
     average_degree(sbm)
 
@@ -31,3 +45,58 @@ function affinities(sbm::AbstractSBM)
     cₒ = d - λ * sqrt(d)
     return (; cᵢ, cₒ)
 end
+
+"""
+    fraction_observed(sbm)
+
+Return the fraction `ρ` of community assignments that are observed.
+"""
+function fraction_observed end
+
+"""
+    sample_graph(rng, sbm, communities)
+
+Sample a graph `g` from an SBM based on known community assignments.
+"""
+function sample_graph(rng::AbstractRNG, sbm::AbstractSBM, communities::Vector{<:Integer})
+    N = length(sbm)
+    (; cᵢ, cₒ) = affinities(sbm)
+    Is, Js = Int[], Int[]
+    for i in 1:N, j in (i + 1):N
+        r = rand(rng)
+        if (
+            ((communities[i] == communities[j]) && (r < cᵢ / N)) ||
+            ((communities[i] != communities[j]) && (r < cₒ / N))
+        )
+            push!(Is, i)
+            push!(Is, j)
+            push!(Js, j)
+            push!(Js, i)
+        end
+    end
+    Vs = fill(true, length(Is))
+    A = sparse(Is, Js, Vs, N, N)
+    g = SimpleWeightedGraph(A)
+    return g
+end
+
+"""
+    sample_mask(rng, sbm, communities)
+
+Sample a vector `Ξ` (Xi) whose components are equal to the community assignments with probability `ρ` and equal to `missing` with probability `1-ρ`. 
+"""
+function sample_mask(rng::AbstractRNG, sbm::AbstractSBM, communities::Vector{<:Integer})
+    N = length(sbm)
+    ρ = fraction_observed(sbm)
+    Ξ = Vector{Union{Missing, Int}}(undef, N)
+    Ξ .= missing
+    for i in 1:N
+        if rand(rng) < ρ
+            Ξ[i] = communities[i]
+        end
+    end
+    return Ξ
+end
+
+prior₊(::Type{R}, Ξᵢ) where {R} = ismissing(Ξᵢ) ? one(R) / 2 : R(Ξᵢ == 1)
+prior₋(::Type{R}, Ξᵢ) where {R} = ismissing(Ξᵢ) ? one(R) / 2 : R(Ξᵢ == -1)