torch_geometric – Pooling Layers
global_add_pool
通过在节点维度上添加节点特征来返回批量图级输出，因此对于单个图
它的输出由下式计算
from torch_geometric.nn import global_mean_pool, global_max_pool, global_add_pool
import torch as th
f = [[1,2,3,4,5], [6,7,8,9,10], [0,0,1,1,1],[2,2,2,0,0],[3,0,3,0,3]]
batch = [0, 0, 0, 1, 1]
f_t = th.tensor(f)
batch_t = th.tensor(batch)
result_add = global_add_pool(f_t, batch_t)
print(result_add)
-----------------------------------
tensor([[ 7, 9, 12, 14, 16],
[ 5, 2, 5, 0, 3]])
global_mean_pool
通过在节点维度上平均节点特征返回批量图级输出，因此对于单个图
它的输出由下式计算
from torch_geometric.nn import global_mean_pool, global_max_pool, global_add_pool
import torch as th
f = [[1,2,3,4,5], [6,7,8,9,10], [0,0,1,1,1],[2,2,2,0,0],[3,0,3,0,3]]
batch = [0, 0, 0, 1, 1]
f_t = th.tensor(f)
batch_t = th.tensor(batch)
result_mean = global_mean_pool(f_t, batch_t)
print(result_mean)
------------------------------
tensor([[2, 3, 4, 4, 5],
[2, 1, 2, 0, 1]])
global_max_pool
通过在节点维度上获取通道方面的最大值来返回批处理图级输出，因此对于单个图
它的输出由下式计算
from torch_geometric.nn import global_mean_pool, global_max_pool, global_add_pool
import torch as th
f = [[1,2,3,4,5], [6,7,8,9,10], [0,0,1,1,1],[2,2,2,0,0],[3,0,3,0,3]]
batch = [0, 0, 0, 1, 1]
f_t = th.tensor(f)
batch_t = th.tensor(batch)
result_max = global_max_pool(f_t, batch_t)
print(result_max)
-------------------------------------------
tensor([[ 6, 7, 8, 9, 10],
[ 3, 2, 3, 0, 3]])
TopKPooling
来自“Graph U-Nets”、“Towards Sparse Hierarchical Graph Classifiers”和“Understanding Attention and Generalization in Graph Neural Networks”论文的 pooling operator
from torch_geometric.nn import TopKPooling
import torch as th
f = [[1,2,3,4,5], [6,7,8,9,10], [0,0,1,1,1], [2,2,2,0,0], [3,0,3,0,3]]
edge_index = [[0,1],[2,0],[3,4]]
batch = [0, 0, 0, 1, 1]
edge_index_t = th.tensor(edge_index)
f_t = th.tensor(f)
batch_t = th.tensor(batch)
topkp = TopKPooling(in_channels=5)
reslut = topkp(x = f_t, edge_index=edge_index_t, batch=batch_t)
print(reslut)
------------------------------------------------------------------
(tensor([[5.9999, 6.9998, 7.9998, 8.9998, 9.9998],
[0.9965, 1.9930, 2.9895, 3.9860, 4.9825],
[2.9566, 0.0000, 2.9566, 0.0000, 2.9566]], grad_fn=<MulBackward0>), tensor([[0],
[1]]), None, tensor([0, 0, 1]), tensor([1, 0, 4]), tensor([1.0000, 0.9965, 0.9855], grad_fn=<IndexBackward0>))
SAGPooling
来自“Self-Attention Graph Pooling”和“Understanding Attention and Generalization in Graph Neural Networks”论文的self-attention pooling算子
EdgePooling
“Towards Graph Pooling by Edge Contraction”和“Edge Contraction Pooling for Graph Neural Networks”论文中的边池运算符。
ASAPooling
“ASAP：Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations”论文中的 Adaptive Structure Aware Pooling 运算符。
PANPooling
“Path Integral Based Convolution and Pooling for Graph Neural Networks”论文中的基于路径积分的池化算子。
MemPooling
来自“Memory-Based Graph Networks”论文的基于内存的池化层，它学习基于软聚类分配的粗化图表示
max_pool
torch_geometric.data.Data根据 中定义的聚类，汇集并粗化对象给出的图cluster。
avg_pool
torch_geometric.data.Data根据 中定义的聚类，汇集并粗化对象给出的图cluster。
max_pool_x
Max-Pools 节点特征根据中定义的聚类cluster。
max_pool_neighbor_x
最大池化相邻节点特征，其中每个特征data.x都被中心节点及其邻居中具有最大值的特征值替换。
avg_pool_x
平均池节点特征根据中定义的聚类cluster。
avg_pool_neighbor_x
平均汇集相邻节点特征，其中每个特征data.x都被中心节点及其邻居的平均特征值替换。
graclus
来自“没有特征向量的加权图切割：多级方法”论文中的一种贪婪聚类算法，该算法选择一个未标记的顶点并将其与其未标记的邻居之一匹配（最大化其边缘权重）。
voxel_grid
来自Graphs论文中卷积网络中的动态边缘条件滤波器的体素网格池，它在点云上覆盖用户定义大小的规则网格，并将所有点聚集在同一体素内。
fps
“PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space”论文中的一种采样算法，该算法针对其余点迭代采样最远的点。
knn
查找kx中最近点中y的每个元素。
knn_graph
计算图形边缘到最近的k点。
radius
在 distance 内的y所有点中查找每个元素。xr
radius_graph
计算给定距离内所有点的图边。
nearest
x将距离y中给定查询点最近的点聚集在一起。
