Biased sampling

cpp/CMakeLists.txt

@@ -310,6 +310,12 @@ set(CUGRAPH_SOURCES
     src/sampling/detail/gather_one_hop_edgelist_mg_v32_e64.cu
     src/sampling/detail/remove_visited_vertices_from_frontier_sg_v32_e32.cu
     src/sampling/detail/remove_visited_vertices_from_frontier_sg_v64_e64.cu
+    src/sampling/detail/check_edge_bias_values_sg_v64_e64.cu
+    src/sampling/detail/check_edge_bias_values_sg_v32_e32.cu
+    src/sampling/detail/check_edge_bias_values_sg_v32_e64.cu
+    src/sampling/detail/check_edge_bias_values_mg_v64_e64.cu
+    src/sampling/detail/check_edge_bias_values_mg_v32_e32.cu
+    src/sampling/detail/check_edge_bias_values_mg_v32_e64.cu
     src/sampling/detail/sample_edges_sg_v64_e64.cu
     src/sampling/detail/sample_edges_sg_v32_e32.cu
     src/sampling/detail/sample_edges_sg_v32_e64.cu
@@ -319,12 +325,12 @@ set(CUGRAPH_SOURCES
     src/sampling/detail/shuffle_and_organize_output_mg_v64_e64.cu
     src/sampling/detail/shuffle_and_organize_output_mg_v32_e32.cu
     src/sampling/detail/shuffle_and_organize_output_mg_v32_e64.cu
-    src/sampling/uniform_neighbor_sampling_mg_v32_e64.cpp
-    src/sampling/uniform_neighbor_sampling_mg_v32_e32.cpp
-    src/sampling/uniform_neighbor_sampling_mg_v64_e64.cpp
-    src/sampling/uniform_neighbor_sampling_sg_v32_e64.cpp
-    src/sampling/uniform_neighbor_sampling_sg_v32_e32.cpp
-    src/sampling/uniform_neighbor_sampling_sg_v64_e64.cpp
+    src/sampling/neighbor_sampling_mg_v32_e64.cpp
+    src/sampling/neighbor_sampling_mg_v32_e32.cpp
+    src/sampling/neighbor_sampling_mg_v64_e64.cpp
+    src/sampling/neighbor_sampling_sg_v32_e64.cpp
+    src/sampling/neighbor_sampling_sg_v32_e32.cpp
+    src/sampling/neighbor_sampling_sg_v64_e64.cpp
     src/sampling/renumber_sampled_edgelist_sg_v64_e64.cu
     src/sampling/renumber_sampled_edgelist_sg_v32_e32.cu
     src/sampling/sampling_post_processing_sg_v64_e64.cu

cpp/include/cugraph/algorithms.hpp

@@ -1872,115 +1872,6 @@ k_core(raft::handle_t const& handle,
        std::optional<raft::device_span<edge_t const>> core_numbers,
        bool do_expensive_check = false);
 
-/**
- * @brief Controls how we treat prior sources in sampling
- *
- * @param DEFAULT    Add vertices encounted while sampling to the new frontier
- * @param CARRY_OVER In addition to newly encountered vertices, include vertices
- *                   used as sources in any previous frontier in the new frontier
- * @param EXCLUDE    Filter the new frontier to exclude any vertex that was
- *                   used as a source in a previous frontier
- */
-enum class prior_sources_behavior_t { DEFAULT = 0, CARRY_OVER, EXCLUDE };
-
-/**
- * @brief Uniform Neighborhood Sampling.
- *
- * This function traverses from a set of starting vertices, traversing outgoing edges and
- * randomly selects from these outgoing neighbors to extract a subgraph.
- *
- * Output from this function is a tuple of vectors (src, dst, weight, edge_id, edge_type, hop,
- * label, offsets), identifying the randomly selected edges.  src is the source vertex, dst is the
- * destination vertex, weight (optional) is the edge weight, edge_id (optional) identifies the edge
- * id, edge_type (optional) identifies the edge type, hop identifies which hop the edge was
- * encountered in.  The label output (optional) identifes the vertex label.  The offsets array
- * (optional) will be described below and is dependent upon the input parameters.
- *
- *
- * If @p starting_vertex_labels is not specified then no organization is applied to the output, the
- * label and offsets values in the return set will be std::nullopt.
- *
- * If @p starting_vertex_labels is specified and @p label_to_output_comm_rank is not specified then
- * the label output has values.  This will also result in the output being sorted by vertex label.
- * The offsets array in the return will be a CSR-style offsets array to identify the beginning of
- * each label range in the data.  `labels.size() == (offsets.size() - 1)`.
- *
- * If @p starting_vertex_labels is specified and @p label_to_output_comm_rank is specified then the
- * label output has values.  This will also result in the output being sorted by vertex label.  The
- * offsets array in the return will be a CSR-style offsets array to identify the beginning of each
- * label range in the data.  `labels.size() == (offsets.size() - 1)`.  Additionally, the data will
- * be shuffled so that all data with a particular label will be on the specified rank.
- *
- * @tparam vertex_t Type of vertex identifiers. Needs to be an integral type.
- * @tparam edge_t Type of edge identifiers. Needs to be an integral type.
- * @tparam weight_t Type of edge weights. Needs to be a floating point type.
- * @tparam edge_type_t Type of edge type. Needs to be an integral type.
- * @tparam label_t Type of label. Needs to be an integral type.
- * @tparam store_transposed Flag indicating whether sources (if false) or destinations (if
- * true) are major indices
- * @tparam multi_gpu Flag indicating whether template instantiation should target single-GPU (false)
- * @param handle RAFT handle object to encapsulate resources (e.g. CUDA stream, communicator, and
- * handles to various CUDA libraries) to run graph algorithms.
- * @param graph_view Graph View object to generate NBR Sampling on.
- * @param edge_weight_view Optional view object holding edge weights for @p graph_view.
- * @param edge_id_view Optional view object holding edge ids for @p graph_view.
- * @param edge_type_view Optional view object holding edge types for @p graph_view.
- * @param starting_vertices Device span of starting vertex IDs for the sampling.
- * In a multi-gpu context the starting vertices should be local to this GPU.
- * @param starting_vertex_labels Optional device span of labels associted with each starting vertex
- * for the sampling.
- * @param label_to_output_comm_rank Optional tuple of device spans mapping label to a particular
- * output rank.  Element 0 of the tuple identifes the label, Element 1 of the tuple identifies the
- * output rank.  The label span must be sorted in ascending order.
- * @param fan_out Host span defining branching out (fan-out) degree per source vertex for each
- * level
- * @param rng_state A pre-initialized raft::RngState object for generating random numbers
- * @param return_hops boolean flag specifying if the hop information should be returned
- * @param prior_sources_behavior Enum type defining how to handle prior sources, (defaults to
- * DEFAULT)
- * @param dedupe_sources boolean flag, if true then if a vertex v appears as a destination in hop X
- * multiple times with the same label, it will only be passed once (for each label) as a source
- * for the next hop.  Default is false.
- * @param with_replacement boolean flag specifying if random sampling is done with replacement
- * (true); or, without replacement (false); default = true;
- * @param do_expensive_check A flag to run expensive checks for input arguments (if set to `true`).
- * @return tuple device vectors (vertex_t source_vertex, vertex_t destination_vertex,
- * optional weight_t weight, optional edge_t edge id, optional edge_type_t edge type,
- * optional int32_t hop, optional label_t label, optional size_t offsets)
- */
-template <typename vertex_t,
-          typename edge_t,
-          typename weight_t,
-          typename edge_type_t,
-          typename label_t,
-          bool store_transposed,
-          bool multi_gpu>
-std::tuple<rmm::device_uvector<vertex_t>,
-           rmm::device_uvector<vertex_t>,
-           std::optional<rmm::device_uvector<weight_t>>,
-           std::optional<rmm::device_uvector<edge_t>>,
-           std::optional<rmm::device_uvector<edge_type_t>>,
-           std::optional<rmm::device_uvector<int32_t>>,
-           std::optional<rmm::device_uvector<label_t>>,
-           std::optional<rmm::device_uvector<size_t>>>
-uniform_neighbor_sample(
-  raft::handle_t const& handle,
-  graph_view_t<vertex_t, edge_t, store_transposed, multi_gpu> const& graph_view,
-  std::optional<edge_property_view_t<edge_t, weight_t const*>> edge_weight_view,
-  std::optional<edge_property_view_t<edge_t, edge_t const*>> edge_id_view,
-  std::optional<edge_property_view_t<edge_t, edge_type_t const*>> edge_type_view,
-  raft::device_span<vertex_t const> starting_vertices,
-  std::optional<raft::device_span<label_t const>> starting_vertex_labels,
-  std::optional<std::tuple<raft::device_span<label_t const>, raft::device_span<int32_t const>>>
-    label_to_output_comm_rank,
-  raft::host_span<int32_t const> fan_out,
-  raft::random::RngState& rng_state,
-  bool return_hops,
-  bool with_replacement                           = true,
-  prior_sources_behavior_t prior_sources_behavior = prior_sources_behavior_t::DEFAULT,
-  bool dedupe_sources                             = false,
-  bool do_expensive_check                         = false);
-
 /*
  * @brief Compute triangle counts.
  *

cpp/include/cugraph/graph.hpp

@@ -319,11 +319,20 @@ struct invalid_idx<
 template <typename vertex_t>
 struct invalid_vertex_id : invalid_idx<vertex_t> {};
 
+template <typename vertex_t>
+inline constexpr vertex_t invalid_vertex_id_v = invalid_vertex_id<vertex_t>::value;
+
 template <typename edge_t>
 struct invalid_edge_id : invalid_idx<edge_t> {};
 
-template <typename vertex_t>
-struct invalid_component_id : invalid_idx<vertex_t> {};
+template <typename edge_t>
+inline constexpr edge_t invalid_edge_id_v = invalid_edge_id<edge_t>::value;
+
+template <typename component_t>
+struct invalid_component_id : invalid_idx<component_t> {};
+
+template <typename component_t>
+inline constexpr component_t invalid_component_id_v = invalid_component_id<component_t>::value;
 
 template <typename vertex_t>
 __host__ __device__ std::enable_if_t<std::is_signed<vertex_t>::value, bool> is_valid_vertex(