pylibcugraphops.operators.update_efeat_e2e_sum_bwd#

pylibcugraphops.operators.update_efeat_e2e_sum_bwd = <nanobind.nb_func object>#

Computes the backward pass for an operation which sums: edge features, and the node features of the source and destination nodes of each each in an edge-to-edge operation.

update_efeat_e2e_sum_bwd(
    grad_input_edge_embedding: Optional[device array],
    grad_input_src_node_embedding: Optional[device array],
    grad_input_dst_node_embedding: Optional[device array],
    grad_output_edge_embedding: device array, graph: pylibcugraphops.bipartite_csc_int[32|64],
    dim_edge: int, stream_id: int = 0
)

Parameters:

grad_input_edge_embeddingdevice array type | None: Device array containing the gradient on the input edge embeddings which is not computed if passed as None
grad_input_src_node_embeddingdevice array type | None: Device array containing the gradient on the input source node embeddings which is not computed if passed as None
grad_input_dst_node_embeddingdevice array type | None: Device array containing the gradient on the input destination node embeddings which is not computed if passed as None
grad_output_edge_embeddingdevice array type: Device array containing the gradient on the output edge embeddings.
graphopaque CSC graph type: graph used for the operation.
dim_edgeint: Dimension of output edge embeddings from the forward pass.
stream_idint, default=0: CUDA stream pointer as a python int