Add DimeNet++ to README

CHANGELOG.md

@@ -5,7 +5,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ## [2.0.5] - 2022-MM-DD
 ### Added
-- Added the `DimeNet++` model ([#4432](https://github.com/pyg-team/pytorch_geometric/pull/4432))
+- Added the `DimeNet++` model ([#4432](https://github.com/pyg-team/pytorch_geometric/pull/4432), [#4699](https://github.com/pyg-team/pytorch_geometric/pull/4699))
 - 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))
 - Added benchmarks via [`wandb`](https://wandb.ai/site) ([#4656](https://github.com/pyg-team/pytorch_geometric/pull/4656), [#4672](https://github.com/pyg-team/pytorch_geometric/pull/4672), [#4676](https://github.com/pyg-team/pytorch_geometric/pull/4676))

README.md

@@ -273,7 +273,7 @@ Our supported GNN models incorporate multiple message passing layers, and users
 Unlike simple stacking of GNN layers, these models could involve pre-processing, additional learnable parameters, skip connections, graph coarsening, etc.
 
 * **[SchNet](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.models.SchNet)** from Schütt *et al.*: [SchNet: A Continuous-filter Convolutional Neural Network for Modeling Quantum Interactions](https://arxiv.org/abs/1706.08566) (NIPS 2017) [[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/qm9_pretrained_schnet.py)]
-* **[DimeNet](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.models.DimeNet)** from Klicpera *et al.*: [Directional Message Passing for Molecular Graphs](https://arxiv.org/abs/2003.03123) (ICLR 2020) [[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/qm9_pretrained_dimenet.py)]
+* **[DimeNet](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.models.DimeNet)** and **[DimeNetPlusPlus](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.models.DimeNetPlusPlus)** from Klicpera *et al.*: [Directional Message Passing for Molecular Graphs](https://arxiv.org/abs/2003.03123) (ICLR 2020) and [Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules](https://arxiv.org/abs/2011.14115) (NeurIPS-W 2020) [[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/qm9_pretrained_dimenet.py)]
 * **[Node2Vec](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.models.Node2Vec)** from Grover and Leskovec: [node2vec: Scalable Feature Learning for Networks](https://arxiv.org/abs/1607.00653) (KDD 2016) [[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/node2vec.py)]
 * **[Deep Graph Infomax](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.models.DeepGraphInfomax)** from Veličković *et al.*: [Deep Graph Infomax](https://arxiv.org/abs/1809.10341) (ICLR 2019) [[**Example1**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/infomax_transductive.py), [**Example2**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/infomax_inductive.py)]
 * **Deep Multiplex Graph Infomax** from Park *et al.*: [Unsupervised Attributed Multiplex Network Embedding](https://arxiv.org/abs/1911.06750) (AAAI 2020) [[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/hetero/dmgi_unsup.py)]

torch_geometric/nn/models/dimenet.py

@@ -220,10 +220,6 @@ def forward(self, x, rbf, sbf, idx_kj, idx_ji):
 
 
 class InteractionPPBlock(torch.nn.Module):
-    """
-    The interaction block transforms each message embedding using
-    multiple residual blocks.
-    """
     def __init__(self, hidden_channels, int_emb_size, basis_emb_size,
                  num_spherical, num_radial, num_before_skip, num_after_skip,
                  act=swish):