torch_geometric.nn.pool.approx_knn

approx_knn(x: Tensor, y: Tensor, k: int, batch_x: Optional[Tensor] = None, batch_y: Optional[Tensor] = None) → Tensor[source]

Finds for each element in y the k approximated nearest points in x.

Note

Approximated \(k\)-nearest neighbor search is performed via the pynndescent library.

Parameters:

  • x (torch.Tensor) – Node feature matrix \(\mathbf{X} \in \mathbb{R}^{N \times F}\).

  • y (torch.Tensor) – Node feature matrix \(\mathbf{X} \in \mathbb{R}^{M \times F}\).

  • k (int) – The number of neighbors.

  • batch_x (torch.Tensor, optional) – Batch vector \(\mathbf{b} \in {\{ 0, \ldots, B-1\}}^N\), which assigns each node to a specific example. (default: None)

  • batch_y (torch.Tensor, optional) – Batch vector \(\mathbf{b} \in {\{ 0, \ldots, B-1\}}^M\), which assigns each node to a specific example. (default: None)

Return type:

torch.Tensor