pylibcugraphops.operators.agg_simple_n2n_e2n_bwd#
- pylibcugraphops.operators.agg_simple_n2n_e2n_bwd = <nanobind.nb_func object>#
- Computes the backward pass for both a simple aggregation (agg_simple) using node features in an
node-to-node reduction (n2n) and a simple aggregation using edge features in an edge-to-node reduction (e2n) on a graph where the results are concatenated.
agg_simple_n2n_e2n_bwd( grad_input_node: device array, grad_input_edge: device array, grad_output: device array, graph: Union[pylibcugraphops.csc_int[32|64], pylibcugraphops.bipartite_csc_int[32|64]], aggregation_operation: pylibcugraphops.operators.AggOp = pylibcugraphops.operators.AggOp.Sum, output_extrema_location: Optional[device array] = None, stream_id: int = 0 ) -> None
- Parameters:
- grad_input_nodedevice array type
Device array containing the output gradient on input node embeddings of forward. Shape:
(graph.n_dst_nodes, dim_in_node)
.- grad_input_edgedevice array type
Device array containing the output gradient on input edge embeddings of forward. Shape:
(n_edges, dim_in_edge)
.- grad_outputdevice array type
Device array containing the input gradient on output embeddings of forward. Shape:
(graph.n_dst_nodes, dim_in_node + dim_in_edge)
.- graphThe opaque graph type
graph used for the operation.
- aggregation_operationAggOp, default=AggOp.Sum
The kind of aggregation operation.
- output_extrema_locationdevice array type | None
Device array containing the location of the min/max embeddings. This is required for min/max aggregation only, and can be
None
otherwise. Shape:(graph.n_dst_nodes, dim_in_node + dim_in_edge)
if set.- stream_idint, default=0
CUDA stream pointer as a python int.