MCPcopy Create free account
hub / github.com/easy-graph/Easy-Graph / e2v

Method e2v

easygraph/classes/hypergraph.py:1662–1679  ·  view source on GitHub ↗

r"""Message passing of ``hyperedges to vertices``. The combination of ``e2v_aggregation`` and ``e2v_update``. Args: ``X`` (``torch.Tensor``): Hyperedge feature matrix. Size :math:`(|\mathcal{E}|, C)`. ``aggr`` (``str``): The aggregation method. Can be ``'mean'``, ``'

(
        self,
        X: torch.Tensor,
        aggr: str = "mean",
        e2v_weight: Optional[torch.Tensor] = None,
        drop_rate: float = 0.0,
    )

Source from the content-addressed store, hash-verified

1660 return X
1661
1662 def e2v(
1663 self,
1664 X: torch.Tensor,
1665 aggr: str = "mean",
1666 e2v_weight: Optional[torch.Tensor] = None,
1667 drop_rate: float = 0.0,
1668 ):
1669 r"""Message passing of ``hyperedges to vertices``. The combination of ``e2v_aggregation`` and ``e2v_update``.
1670
1671 Args:
1672 ``X`` (``torch.Tensor``): Hyperedge feature matrix. Size :math:`(|\mathcal{E}|, C)`.
1673 ``aggr`` (``str``): The aggregation method. Can be ``'mean'``, ``'sum'`` and ``'softmax_then_sum'``.
1674 ``e2v_weight`` (``torch.Tensor``, optional): The weight vector attached to connections (hyperedges point to vertices). If not specified, the function will use the weights specified in hypergraph construction. Defaults to ``None``.
1675 ``drop_rate`` (``float``): Dropout rate. Randomly dropout the connections in incidence matrix with probability ``drop_rate``. Default: ``0.0``.
1676 """
1677 X = self.e2v_aggregation(X, aggr, e2v_weight, drop_rate=drop_rate)
1678 X = self.e2v_update(X)
1679 return X
1680
1681 def e2v_of_group(
1682 self,

Callers 1

v2vMethod · 0.95

Calls 2

e2v_aggregationMethod · 0.95
e2v_updateMethod · 0.95

Tested by

no test coverage detected