The first pyg-lib release will focus on unifying the implementations from torch-sparse and torch-cluster into a single package in order to reduce the number of external low-level library dependencies of PyG.
In addition, implementations will be improved, e.g., by out-sourcing common routines into re-usable building blocks, unifiying the interfaces, supporting various data types, biased sampling, etc.
New functionality will be integrated for temporal-based learning and GNN acceleration.
The first
pyg-lib
release will focus on unifying the implementations fromtorch-sparse
andtorch-cluster
into a single package in order to reduce the number of external low-level library dependencies of PyG. In addition, implementations will be improved, e.g., by out-sourcing common routines into re-usable building blocks, unifiying the interfaces, supporting various data types, biased sampling, etc. New functionality will be integrated for temporal-based learning and GNN acceleration.Samplers
Priority 0
int32
,int64
, etccugraph
dependencyneighbor_sample(rowptr, col, seed, num_neighbors)
:replace
: sampling with or without replacementdirected
: sub-tree vs sub-graph sampling (CPU-only)disjoint
: disjoint subtrees for every seed node (CPU-only)temporal
: temporal sampling (CPU-only)weighted
: Support for biased sampling (CPU-only)temporal_weighted
: Support for biased temporal sampling (CPU-only)return_edge_id
: Support for returning edge IDs (CPU-only)subgraph_sample(rowptr, col, nodes)
:return_edge_id
: Support for returning edge IDs (CPU-only)Priority 1
random_walk(rowptr, col, nodes)
:weighted
: Support for biased sampling (CPU-only)node2vec
-based sampling (CPU-only)return_edge_id
: Support for returning edge IDs (CPU-only)hgt_sample(rowptr, dict, seed)
:weighted
: Support for biased sampling (CPU-only)Operators
Priority 0
segment_matmul(src, ptr, other)
:forward
(CPU+GPU)backward
(CPU+GPU)Priority 1
sparse_softmax(src, index)
:forward
(CPU+GPU) (#135)backward
(CPU+GPU)Others
Priority 0 (refactor only)
METIS
graph partitioningfps
k-NN
graph generationradius
graph generation/ball queryPriority 1
int32
,int64
, etc