v0.6.15

GraphNeuralNetworks v0.6.15

Diff since v0.6.14

Merged pull requests:

• example correction (#347) (@eahenle)
• CompatHelper: add new compat entry for Statistics at version 1, (keep existing compat) (#350) (@github-actions[bot])
• Set compatibilities for standard packages (#352) (@bicycle1885)
• Relax CUDA compatibility (#353) (@bicycle1885)

Closed issues:

• Error in Example Code (#346)
• Outdated default package installation (#348)
• View arrays on GPU cause scalar indexing error (#349)

v0.6.14

GraphNeuralNetworks v0.6.14

Diff since v0.6.13

Merged pull requests:

• batch wider eltype (#340) (@CarloLucibello)
• Remove type constraints on Flux.batch for GNNHeteroGraph (#342) (@AarSeBail)

Closed issues:

• The constraint in Flux.batch(gs::AbstractVector{<:GNNHeteroGraph}) does not seem to be strong enough (#341)

v0.6.13

GraphNeuralNetworks v0.6.13

Diff since v0.6.12

Closed issues:

• Edge weights not properly documented for GNNHeteroGraphs (and implement new function to add new edge weights?) (#331)

Merged pull requests:

• Bump actions/checkout from 3 to 4 (#336) (@dependabot[bot])
• improve add_edges for graph and heterographs (#337) (@CarloLucibello)
• extend reduce_nodes and graph_indicator for heterographs (#339) (@CarloLucibello)

v0.6.12

GraphNeuralNetworks v0.6.12

Diff since v0.6.11

Closed issues:

• Update Flux.trainable (#323)
• HeteroGraphConv bug: ERROR: duplicate field name in NamedTuple: "movie" is not unique (#332)
• add_edges for GNNHeteroGraph does not allow providing the number of nodes (#334)

Merged pull requests:

• Update Flux.trainable (#330) (@aurorarossi)
• Fix heteroconv aggregation + tests (#333) (@svilupp)
• fixes add_edges + adds tests (#335) (@svilupp)

v0.6.11

GraphNeuralNetworks v0.6.11

Diff since v0.6.10

Closed issues:

• AGNNConv behaviour different from mathematical definition (due to self loops) (#325)

Merged pull requests:

• Add temporal graph documentation (#327) (@aurorarossi)
• fix AGNNConv docstring and add other options (#328) (@CarloLucibello)

v0.6.10

GraphNeuralNetworks v0.6.10

Diff since v0.6.9

Merged pull requests:

• Add TGCNCell layer (#314) (@aurorarossi)
• Add Flux.Recur and TGCN (#319) (@aurorarossi)
• Fix typos and julia-repl text (#320) (@aurorarossi)
• Add traffic prediction example (#321) (@aurorarossi)
• Add A3TGCN model (#322) (@aurorarossi)
• Add traffic prediction tutorial (#324) (@aurorarossi)
• Julia repl rendering fix (#326) (@aurorarossi)

v0.6.9

GraphNeuralNetworks v0.6.9

Diff since v0.6.8

Closed issues:

• use extension instead of CUDA hard dependence (#317)

Merged pull requests:

• Remove CUDA dependence in favor of extension (#318) (@CarloLucibello)

v0.6.8

GraphNeuralNetworks v0.6.8

Diff since v0.6.7

Closed issues:

• Implement Learnable Structural Positional Encoding (LSPE) (#190)
• add docs for HeteroGraphConv (#302)
• add batching for GNNHeteroGraph (#303)

Merged pull requests:

• Add random temporal hyperbolic graph (#313) (@aurorarossi)
• move to Flux 0.14 (#316) (@CarloLucibello)

v0.6.7

GraphNeuralNetworks v0.6.7

Diff since v0.6.6

Closed issues:

• Convolutions for GNNHeteroGraphs (#254)
• need more informative error for dimension mismatch (#283)
• Local pooling in graph regression/classification problems (#307)

Merged pull requests:

• Improve error description of setproperty! (#287) (@aurorarossi)
• Fix spacing in documentation example (#289) (@asinghvi17)
• Fix typos (#290) (@aurorarossi)
• Add TemporalSnapshotsGNNGraph struct (#293) (@aurorarossi)
• Add docstrings for TemporalSnapshotsGNNgraph (#294) (@aurorarossi)
• modernize examples and create example notebooks (#295) (@CarloLucibello)
• make add_snapshot non mutating (#296) (@CarloLucibello)
• Add getproperty function to TemporalSnapshotsGNNGraph (#297) (@aurorarossi)
• [heterograph] add has_edge, get_index, add_edges (#298) (@CarloLucibello)
• HeteroGraphConv implementation (#300) (@CarloLucibello)
• update examples to explicit gradient (#301) (@CarloLucibello)
• improvement for differentiability with heterogeneous graphs (#304) (@CarloLucibello)
• Add Temporal random radius graph generator (#305) (@aurorarossi)
• CompatHelper: bump compat for NNlib to 0.9, (keep existing compat) (#306) (@github-actions[bot])
• Flux.batch for GNNHeteroGraph (#309) (@CarloLucibello)
• heterograph guide (#310) (@CarloLucibello)
• HeteroGraphConv documentation (#312) (@CarloLucibello)

v0.6.6

GraphNeuralNetworks v0.6.6

Diff since v0.6.5

Closed issues:

• add_edges adds a non-existent edge to its DataStore (#280)

Merged pull requests:

• Fix few typos in tutorials (#278) (@natema)
• CompatHelper: bump compat for StatsBase to 0.34, (keep existing compat) (#279) (@github-actions[bot])
• Fix a few typos (#281) (@pitmonticone)
• fix cat empty features (#286) (@CarloLucibello)