v0.3.10

GraphNeuralNetworks v0.3.10

Diff since v0.3.9

Closed issues:

• Implement add_reverse_edges (#103)
• propagate() is 20x slower than built-in sparse matmul (#106)
• add fusing propagate specialization for e_mul_xj (#108)
• implement set_edge_weights (#110)

Merged pull requests:

• fused e_mul_xj and weighted option for adjacency_matrix (#107) (@CarloLucibello)
• Typecast GNNGraph.num_nodes to Int (#109) (@abieler)
• Potential Spelling fix (#111) (@umbriquse)
• add w_mul_xj and set_edge_weight (#114) (@CarloLucibello)
• support for aggregating edge feature in remove_multi_edges (#115) (@CarloLucibello)
• add to_bidirected (#116) (@CarloLucibello)
• add Google Summer of Code [GSOC] doc page (#117) (@CarloLucibello)
• CompatHelper: bump compat for NNlib to 0.8, (keep existing compat) (#119) (@github-actions[bot])

v0.3.9

GraphNeuralNetworks v0.3.9

Diff since v0.3.8

Closed issues:

• Problem with InlineStrings.jl (#98)
• Include undirected graphs (#101)
• Merging multiple feature arrays (#102)
• conflict with CSV and GNNGraphs when running Flux.batch (#104)

Merged pull requests:

• workaround for sort ambiguity in cat_features (#105) (@CarloLucibello)

v0.3.8

GraphNeuralNetworks v0.3.8

Diff since v0.3.7

Closed issues:

• Custom Function GPU Compatibitlity Issue: Indexing (#91)
• Flux.batch Overloading for Generators (#92)
• outputsize for GNNChain (#96)

Merged pull requests:

• add sample_neighbors (#93) (@CarloLucibello)
• CompatHelper: bump compat for LearnBase to 0.6, (keep existing compat) (#95) (@github-actions[bot])
• Adds GATv2 layer (#97) (@abieler)

v0.3.7

GraphNeuralNetworks v0.3.7

Diff since v0.3.6

Closed issues:

• Hash function for GNNGraph (#87)
• no method matching getobs(::NamedTuple{(:x,), Tuple{Matrix{Float32}}} (#88)

Merged pull requests:

• GeometricFlux cora comparison (#82) (@CarloLucibello)
• implement MEGNetConv (#83) (@CarloLucibello)
• small doc update (#84) (@CarloLucibello)
• export get_edge_weight + use weights from adjacency matrix (#86) (@CarloLucibello)
• don't rely on LearnBase.getobs (#90) (@CarloLucibello)

v0.3.6

GraphNeuralNetworks v0.3.6

Diff since v0.3.5

Merged pull requests:

• Fixed typos in the docs (#78) (@pitmonticone)
• implement nearest neighbors graph (#79) (@CarloLucibello)

v0.3.5

GraphNeuralNetworks v0.3.5

Diff since v0.3.4

Closed issues:

• add support to edge weight in GCNConv (#40)

Merged pull requests:

• Support edge weights in GCNConv (#76) (@CarloLucibello)
• remove nodetype for eltype (#77) (@CarloLucibello)

v0.3.4

GraphNeuralNetworks v0.3.4

Diff since v0.3.3

Closed issues:

• Differences to GeometricFlux.jl? (#2)

Merged pull requests:

• improve docs (#72) (@CarloLucibello)
• minor doc improve (#73) (@CarloLucibello)
• fix has_multi_edges (#75) (@CarloLucibello)

v0.3.3

GraphNeuralNetworks v0.3.3

Diff since v0.3.2

Closed issues:

• graph NeuralODE example not working on gpu (#56)

Merged pull requests:

• add link prediction example (#61) (@CarloLucibello)
• have GNNGraph inherit from Graphs.AbstractGraph (#63) (@CarloLucibello)
• refactor GNNGraph into submodule + implement add_edges (#64) (@CarloLucibello)
• implement unbatch and add_nodes (#65) (@CarloLucibello)
• NeuralODE example working on cpu and gpu (#67) (@CarloLucibello)
• add AGNNConv (#68) (@CarloLucibello)
• better negative sampling + remove_multi_edges + is_bidirected + DotDecoder (#69) (@CarloLucibello)
• improvements to link prediction (#70) (@CarloLucibello)
• bidirected graph support in rand_split_edge (#71) (@CarloLucibello)

v0.3.2

GraphNeuralNetworks v0.3.2

Diff since v0.3.1

Merged pull requests:

• implement StatsBase.nobs instead of LearnBase.nobs (#62) (@CarloLucibello)

v0.3.1

GraphNeuralNetworks v0.3.1

Diff since v0.3.0

Merged pull requests:

• add GlobalAttentionPool (#58) (@CarloLucibello)
• add softmax_edge_neighbors (#59) (@CarloLucibello)