tfgnn.HyperAdjacency

View source on GitHub

Stores how (hyper-)edges connect tuples of nodes from incident node sets.

tfgnn.HyperAdjacency(
    data: Data, spec: 'GraphPieceSpecBase'
)

The incident node sets in the hyper-adjacency are referenced by a unique integer identifier called the node set tag. (For a non-hyper graph, it is conventional to use the integers tfgnn.SOURCE and tfgnn.TARGET.) This allows the hyper-adjacency to connect nodes from the same or different node sets. Each hyper-edge connects a fixed number of nodes, one node from each incident node set. The adjacency information is stored as a mapping from the node set tags to integer tensors containing indices of nodes in corresponding node sets. Those tensors are indexed by edges. All index tensors have the same type spec and shape of [*graph_shape, num_edges], where num_edges is the number of edges in the edge set (could be potentially ragged). The index tensors are of tf.Tensor type if num_edges is not None or graph_shape.rank = 0 and of tf.RaggedTensor type otherwise.

The HyperAdjacency is a composite tensor.

Args
data	Nest of Field or subclasses of GraphPieceBase.
spec	A subclass of GraphPieceSpecBase with a _data_spec that matches data.

Attributes
indices_dtype	The dtype for graph items indexing. One of tf.int32 or tf.int64.
rank	The rank of this Tensor. Guaranteed not to be None.
row_splits_dtype	The dtype for ragged row partitions. One of tf.int32 or tf.int64.
shape	A possibly-partial shape specification for this Tensor. The returned tf.TensorShape is guaranteed to have a known rank and no unknown dimensions except possibly the outermost.
spec	The public type specification of this tensor.

Methods

from_indices

View source

@classmethod
from_indices(
    indices: Indices, *_, validate: Optional[bool] = None
) -> 'HyperAdjacency'

Constructs a new instance from the indices tensors.

Example 1:

# Single graph (rank is 0). Connects pairs of nodes (a[0], b[2]),
# (a[1], b[1]), (a[2], b[0]) from node sets a and b.
tfgnn.HyperAdjacency.from_indices({
    tfgnn.SOURCE: ('a', [0, 1, 2]),
    tfgnn.TARGET: ('b', [2, 1, 0])
})

Example 2:

# Single hypergraph (rank is 0). Connects triplets of nodes
# (a[0], b[2], c[1]), (a[1], b[1], c[0]) from the node sets a, b and c.
tfgnn.HyperAdjacency.from_indices({
    0: ('a', [0, 1]),
    1: ('b', [2, 1]),
    2: ('c', [1, 0]),
})

Example 3:

# Batch of two graphs (rank is 1). Connects pairs of nodes in
# graph 0: (a[0], b[2]), (a[1], b[1]); graph 1: (a[2], b[0]).
tfgnn.HyperAdjacency.from_indices({
    tfgnn.SOURCE: ('a', tf.ragged.constant([[0, 1], [2]])),
    tfgnn.TARGET: ('b', tf.ragged.constant([[2, 1], [0]])),
})

Args
indices	A mapping from node tags to 2-tuples of node set name and node index tensor. The index tensors must have the same type spec and shape of [*graph_shape, num_edges], where num_edges is the number of edges in each graph (could be ragged). The index tensors are of tf.Tensor type if num_edges is not None or graph_shape.rank = 0 and of tf.RaggedTensor type otherwise.
validate	If True, checks that node indices have the same type spec.

Returns
A HyperAdjacency tensor with its shape and indices_dtype being inferred from the passed indices values.

get_indices_dict

View source

get_indices_dict() -> Dict[IncidentNodeTag, Tuple[NodeSetName, Field]]

Returns copy of indices as a dictionary.

node_set_name

View source

node_set_name(
    node_set_tag: IncidentNodeTag
) -> NodeSetName

Returns a node set name for the given node set tag.

set_shape

View source

set_shape(
    new_shape: ShapeLike
) -> 'GraphPieceBase'

Deprecated. Use with_shape().

with_indices_dtype

View source

with_indices_dtype(
    dtype: tf.dtypes.DType
) -> 'GraphPieceBase'

Returns a copy of this piece with the given indices dtype.

with_row_splits_dtype

View source

with_row_splits_dtype(
    dtype: tf.dtypes.DType
) -> 'GraphPieceBase'

Returns a copy of this piece with the given row splits dtype.

with_shape

View source

with_shape(
    new_shape: ShapeLike
) -> 'GraphPieceBase'

Enforce the common prefix shape on all the contained features.

__getitem__

View source

__getitem__(
    node_set_tag: IncidentNodeTag
) -> tfgnn.Field

Returns an index tensor for the given node set tag.