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,
)
| 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, |
no test coverage detected