Missing functionality compared to DGL

Checklist of stuff we miss compared to Deep Graph Library.
PRs are welcome!

Conv Layers

• GraphConv (called GCNConv here)
• EdgeWeightNorm
• RelGraphConv
• TAGConv
• GATConv
• EdgeConv
• SAGEConv
• SGConv
• APPNPConv
• GINConv
• GatedGraphConv
• GMMConv (#147)
• ChebConv
• AGNNConv
• NNConv
• AtomicConv
• CFConv
• DotGatConv
• TWIRLSConv
• TWIRLSUnfoldingAndAttention
• GCN2Conv

Dense Conv Layers

• DenseGraphConv
• DenseSAGEConv
• DenseChebConv

Global Pooling Layers

• SumPooling (GlobalPooling(+) here)
• AvgPooling (GlobalPooling(mean) here)
• MaxPooling (GlobalPooling(max) here)
• SortPooling
• WeightAndSum
• GlobalAttentionPooling
• Set2Set
• SetTransformerEncoder
• SetTransformerDecoder

Batching and Reading Out Ops

https://docs.dgl.ai/en/0.6.x/api/python/dgl.html#batching-and-reading-out-ops

• batch. Use Flux.batch or SparseArrays.blockdiag
• unbatch
• readout_nodes (called reduce_nodes here)
• readout_edges (called reduce_edges here)
• sum_nodes # use reduce_nodes(+, g, x)
• sum_edges # use reduce_edges(+, g, x)
• mean_nodes
• mean_edges
• max_nodes
• max_edges
• softmax_nodes
• softmax_edges
• broadcast_nodes
• broadcast_edges
• topk_nodes
• topk_edges

Adjacency Related Utilities

• khop_adj
• laplacian_lambda_max

nn.functional

https://docs.dgl.ai/api/python/nn.functional.html

• edge_softmax (softmax_edge_neighbors here)

optim

https://docs.dgl.ai/api/python/dgl.optim.html

• Sparse Adam
• Sparse AdaGrad

nn Utility Modules

• Sequential (GNNChain here)
• WeightBasis
• KNNGraph
• SegmentedKNNGraph

nn NodeEmbedding Module

• NodeEmbedding

Sampling and Stochastic training

.....

Distributed Training

....

Start with the DGL Python API links and choose one unchecked capability from the checklist, such as a convolution, pooling layer, or sampling operation. Compare its expected behavior with the corresponding GraphNeuralNetworks.jl conventions; the work is done when that selected item is implemented and its checklist entry can be marked complete.