Update SoftmaxAggregation and PowerMeanAggregation doc strings (#…

…5036) * Update softmax and powermean aggrs docs * changelog * update Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de> * update Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de> * update Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de> * update Co-authored-by: Guohao Li <lighaime@gmail.com> Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
pyg-team · Jul 23, 2022 · 6ed5caf · 6ed5caf
1 parent 6864a1b
commit 6ed5caf
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 5 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -37,7 +37,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Added the `bias` vector to the `GCN` model definition in the "Create Message Passing Networks" tutorial ([#4755](https://github.com/pyg-team/pytorch_geometric/pull/4755))
 - Added `transforms.RootedSubgraph` interface with two implementations: `RootedEgoNets` and `RootedRWSubgraph` ([#3926](https://github.com/pyg-team/pytorch_geometric/pull/3926))
 - Added `ptr` vectors for `follow_batch` attributes within `Batch.from_data_list` ([#4723](https://github.com/pyg-team/pytorch_geometric/pull/4723))
-- Added `torch_geometric.nn.aggr` package ([#4687](https://github.com/pyg-team/pytorch_geometric/pull/4687), [#4721](https://github.com/pyg-team/pytorch_geometric/pull/4721), [#4731](https://github.com/pyg-team/pytorch_geometric/pull/4731), [#4762](https://github.com/pyg-team/pytorch_geometric/pull/4762), [#4749](https://github.com/pyg-team/pytorch_geometric/pull/4749), [#4779](https://github.com/pyg-team/pytorch_geometric/pull/4779), [#4863](https://github.com/pyg-team/pytorch_geometric/pull/4863), [#4864](https://github.com/pyg-team/pytorch_geometric/pull/4864), [#4865](https://github.com/pyg-team/pytorch_geometric/pull/4865), [#4866](https://github.com/pyg-team/pytorch_geometric/pull/4866), [#4872](https://github.com/pyg-team/pytorch_geometric/pull/4872), [#4934](https://github.com/pyg-team/pytorch_geometric/pull/4934), [#4935](https://github.com/pyg-team/pytorch_geometric/pull/4935), [#4957](https://github.com/pyg-team/pytorch_geometric/pull/4957), [#4973](https://github.com/pyg-team/pytorch_geometric/pull/4973),[#4973](https://github.com/pyg-team/pytorch_geometric/pull/4973), [#4986](https://github.com/pyg-team/pytorch_geometric/pull/4986), [#4995](https://github.com/pyg-team/pytorch_geometric/pull/4995), [#5000](https://github.com/pyg-team/pytorch_geometric/pull/5000), [#5034](https://github.com/pyg-team/pytorch_geometric/pull/5034))
+- Added `torch_geometric.nn.aggr` package ([#4687](https://github.com/pyg-team/pytorch_geometric/pull/4687), [#4721](https://github.com/pyg-team/pytorch_geometric/pull/4721), [#4731](https://github.com/pyg-team/pytorch_geometric/pull/4731), [#4762](https://github.com/pyg-team/pytorch_geometric/pull/4762), [#4749](https://github.com/pyg-team/pytorch_geometric/pull/4749), [#4779](https://github.com/pyg-team/pytorch_geometric/pull/4779), [#4863](https://github.com/pyg-team/pytorch_geometric/pull/4863), [#4864](https://github.com/pyg-team/pytorch_geometric/pull/4864), [#4865](https://github.com/pyg-team/pytorch_geometric/pull/4865), [#4866](https://github.com/pyg-team/pytorch_geometric/pull/4866), [#4872](https://github.com/pyg-team/pytorch_geometric/pull/4872), [#4934](https://github.com/pyg-team/pytorch_geometric/pull/4934), [#4935](https://github.com/pyg-team/pytorch_geometric/pull/4935), [#4957](https://github.com/pyg-team/pytorch_geometric/pull/4957), [#4973](https://github.com/pyg-team/pytorch_geometric/pull/4973), [#4973](https://github.com/pyg-team/pytorch_geometric/pull/4973), [#4986](https://github.com/pyg-team/pytorch_geometric/pull/4986), [#4995](https://github.com/pyg-team/pytorch_geometric/pull/4995), [#5000](https://github.com/pyg-team/pytorch_geometric/pull/5000), [#5034](https://github.com/pyg-team/pytorch_geometric/pull/5034), [#5036](https://github.com/pyg-team/pytorch_geometric/pull/5036))
 - Added the `DimeNet++` model ([#4432](https://github.com/pyg-team/pytorch_geometric/pull/4432), [#4699](https://github.com/pyg-team/pytorch_geometric/pull/4699), [#4700](https://github.com/pyg-team/pytorch_geometric/pull/4700), [#4800](https://github.com/pyg-team/pytorch_geometric/pull/4800))
 - Added an example of using PyG with PyTorch Ignite ([#4487](https://github.com/pyg-team/pytorch_geometric/pull/4487))
 - Added `GroupAddRev` module with support for reducing training GPU memory ([#4671](https://github.com/pyg-team/pytorch_geometric/pull/4671), [#4701](https://github.com/pyg-team/pytorch_geometric/pull/4701), [#4715](https://github.com/pyg-team/pytorch_geometric/pull/4715), [#4730](https://github.com/pyg-team/pytorch_geometric/pull/4730))

diff --git a/torch_geometric/nn/aggr/basic.py b/torch_geometric/nn/aggr/basic.py
@@ -72,10 +72,9 @@ class SoftmaxAggregation(Aggregation):
     <https://arxiv.org/abs/2006.07739>`_ paper
 
     .. math::
-        \mathrm{softmax}(\{ \mathbf{x}_i : i \in |\mathcal{X}| \}, t)
-        = \sum_{i \in |\mathcal{X}|} \frac{ \exp( t \cdot \mathbf{x}_i)}
-        {\sum_{j \in |\mathcal{X}|} \exp(t \cdot \mathbf{x}_j)}
-        \cdot \mathbf{x}_{i},
+        \mathrm{softmax}(\mathcal{X}|t) = \sum_{\mathbf{x}_i\in\mathcal{X}}
+        \frac{\exp(t\cdot\mathbf{x}_i)}{\sum_{\mathbf{x}_j\in\mathcal{X}}
+        \exp(t\cdot\mathbf{x}_j)}\cdot\mathbf{x}_{i},
 
     where :math:`t` controls the softness of the softmax when aggregating over
     a set of features :math:`\mathcal{X}`.
@@ -130,6 +129,24 @@ def __repr__(self) -> str:
 
 
 class PowerMeanAggregation(Aggregation):
+    r"""The powermean aggregation operator based on a power term, as
+    described in the `"DeeperGCN: All You Need to Train Deeper GCNs"
+    <https://arxiv.org/abs/2006.07739>`_ paper
+
+    .. math::
+        \mathrm{powermean}(\mathcal{X}|p) = \left(\frac{1}{|\mathcal{X}|}
+        \sum_{\mathbf{x}_i\in\mathcal{X}}\mathbf{x}_i^{p}\right)^{1/p},
+
+    where :math:`p` controls the power of the powermean when aggregating over
+    a set of features :math:`\mathcal{X}`.
+
+    Args:
+        p (float, optional): Initial power for powermean aggregation.
+            (default: :obj:`1.0`)
+        learn (bool, optional): If set to :obj:`True`, will learn the value
+            :obj:`p` for powermean aggregation dynamically.
+            (default: :obj:`False`)
+    """
     def __init__(self, p: float = 1.0, learn: bool = False):
         # TODO Learn distinct `p` per channel.
         super().__init__()