From 9963fcfefcc41522b7fe9b955c1a1a094e364e82 Mon Sep 17 00:00:00 2001 From: Matthias Fey Date: Tue, 24 May 2022 07:54:21 +0200 Subject: [PATCH] Add `DimeNet++` to `README` (#4699) * add dimenet++ readme * changelog --- CHANGELOG.md | 2 +- README.md | 2 +- torch_geometric/nn/models/dimenet.py | 4 ---- 3 files changed, 2 insertions(+), 6 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index bbc2792c91d9..a1929eceabe8 100644 --- a/CHANGELOG.md +++ b/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)) diff --git a/README.md b/README.md index 9d2ce26123ad..a9e738ca0ada 100644 --- a/README.md +++ b/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)] diff --git a/torch_geometric/nn/models/dimenet.py b/torch_geometric/nn/models/dimenet.py index a9760852bcc9..327ec2fd19b7 100644 --- a/torch_geometric/nn/models/dimenet.py +++ b/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):