Skip to content

docs: fix broken links for FusedGATConv and MoleculeGPT and fix typo #10527

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

docs: fix broken links for FusedGATConv and MoleculeGPT and fix typo #10527

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7088cb5
Apply mdformat autoformatting from pre-commit
supawesome Nov 9, 2025
e1f2fd3
Merge branch 'master' into fix-doc-links
supawesome Nov 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,7 +217,7 @@ These GNN layers can be stacked together to create Graph Neural Network models.
- **[HGTConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.HGTConv.html)** from Hu *et al.*: [Heterogeneous Graph Transformer](https://arxiv.org/abs/2003.01332) (WWW 2020) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/hetero/hgt_dblp.py)\]
- **[HEATConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.HEATonv.html)** from Mo *et al.*: [Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction](https://arxiv.org/abs/2106.07161) (CoRR 2021)
- **[SSGConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.SSGConv.html)** from Zhu *et al.*: [Simple Spectral Graph Convolution](https://openreview.net/forum?id=CYO5T-YjWZV) (ICLR 2021)
- **[FusedGATConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.FusedGATConv.html)** from Zhang *et al.*: [Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective](https://proceedings.mlsys.org/paper/2022/file/9a1158154dfa42caddbd0694a4e9bdc8-Paper.pdf) (MLSys 2022)
- **[FusedGATConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.FusedGATConv.html)** from Zhang *et al.*: [Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective](https://proceedings.mlsys.org/paper_files/paper/2022/file/b559156047e50cf316207249d0b5a6c5-Paper.pdf) (MLSys 2022)
- **[GPSConv](https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.nn.conv.GPSConv.html)** from Rampášek *et al.*: [Recipe for a General, Powerful, Scalable Graph Transformer](https://arxiv.org/abs/2205.12454) (NeurIPS 2022) \[[**Example**](https://github.com/pyg-team/pytorch_geometric/blob/master/examples/graph_gps.py)\]

</details>
Expand Down
18 changes: 9 additions & 9 deletions examples/llm/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
# Examples for Co-training LLMs and GNNs

| Example | Description |
| -------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`g_retriever.py`](./g_retriever.py) | Example helper functions for how to use the [G-retriever](https://arxiv.org/abs/2402.07630) GNN+LLM module in PyG. We also have an [example repo](https://github.com/neo4j-product-examples/neo4j-gnn-llm-example) for integration with [Neo4j Graph DBs](neo4j.com) along with an associated [blog](https://developer.nvidia.com/blog/boosting-qa-accuracy-with-graphrag-using-pyg-and-graph-databases/) showing 2x accuracy gains over LLMs on real medical data. See examples/llm/txt2kg_rag.py for e2e pipeline in PyG including: KG Creation, Subgraph Retrieval, GNN+LLM Finetuning, Testing, LLM Judge Eval. |
| [`nvtx_examples/`](./nvtx_examples/) | Contains examples of how to wrap functions using the NVTX profiler for CUDA runtime analysis. |
| [`molecule_gpt.py`](./molecule_gpt.py) | Example for MoleculeGPT: Instruction Following Large Language Models for Molecular Property Prediction. Supports MoleculeGPT and InstructMol dataset |
| [`glem.py`](./glem.py) | Example for [GLEM](https://arxiv.org/abs/2210.14709), a GNN+LLM co-training model via variational Expectation-Maximization (EM) framework on node classification tasks to achieve SOTA results |
| [`git_mol.py`](./git_mol.py) | Example for GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text |
| [`protein_mpnn.py`](./protein_mpnn.py) | Example for [Robust deep learning--based protein sequence design using ProteinMPNN](https://www.biorxiv.org/content/10.1101/2022.06.03.494563v1) |
| [`txt2kg_rag.py`](./txt2kg_rag.py) | Full end 2 end RAG pipeline using TXT2KG and Vector and Graph RAG with a GNN to achieve state of the art results. Uses the [techQA dataset](https://paperswithcode.com/dataset/techqa) but can be extended to handle any RAG dataset with a corpus of documents and an associated set of Q+A pairs to be split for train/eval/test. See [Stanford GNN+LLM Talk](https://www.nvidia.com/en-us/on-demand/session/other25-nv-0003/) for more details. Note that the TechQA data requires only a single document to answer each question so it can be viewed as a toy example. To see significant accuracy boosts from GNN+LLM TXT2KG based RAG, use data that requires multiple text chunks to answer a question. In cases where single document can answer, basic RAG should be sufficient. |
| Example | Description |
| -------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`g_retriever.py`](./g_retriever.py) | Example helper functions for how to use the [G-retriever](https://arxiv.org/abs/2402.07630) GNN+LLM module in PyG. We also have an [example repo](https://github.com/neo4j-product-examples/neo4j-gnn-llm-example) for integration with [Neo4j Graph DBs][neo4j.com] along with an associated [blog](https://developer.nvidia.com/blog/boosting-qa-accuracy-with-graphrag-using-pyg-and-graph-databases/) showing 2x accuracy gains over LLMs on real medical data. See examples/llm/txt2kg_rag.py for e2e pipeline in PyG including: KG Creation, Subgraph Retrieval, GNN+LLM Finetuning, Testing, LLM Judge Eval. |
| [`nvtx_examples/`](./nvtx_examples/) | Contains examples of how to wrap functions using the NVTX profiler for CUDA runtime analysis. |
| [`molecule_gpt.py`](./molecule_gpt.py) | Example for [MoleculeGPT: Instruction Following Large Language Models for Molecular Property Prediction](https://ai4d3.github.io/2023/papers/34.pdf). Supports MoleculeGPT and InstructMol dataset |
| [`glem.py`](./glem.py) | Example for [GLEM](https://arxiv.org/abs/2210.14709), a GNN+LLM co-training model via variational Expectation-Maximization (EM) framework on node classification tasks to achieve SOTA results |
| [`git_mol.py`](./git_mol.py) | Example for [GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text](https://arxiv.org/abs/2308.06911) |
| [`protein_mpnn.py`](./protein_mpnn.py) | Example for [Robust deep learning based protein sequence design using ProteinMPNN](https://www.biorxiv.org/content/10.1101/2022.06.03.494563v1) |
| [`txt2kg_rag.py`](./txt2kg_rag.py) | Full end 2 end RAG pipeline using TXT2KG and Vector and Graph RAG with a GNN to achieve state of the art results. Uses the [techQA dataset](https://arxiv.org/abs/1911.02984) but can be extended to handle any RAG dataset with a corpus of documents and an associated set of Q+A pairs to be split for train/eval/test. See [Stanford GNN+LLM Talk](https://www.nvidia.com/en-us/on-demand/session/other25-nv-0003/) for more details. Note that the TechQA data requires only a single document to answer each question so it can be viewed as a toy example. To see significant accuracy boosts from GNN+LLM TXT2KG based RAG, use data that requires multiple text chunks to answer a question. In cases where single document can answer, basic RAG should be sufficient. |
2 changes: 1 addition & 1 deletion examples/llm/molecule_gpt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
"""This example implements the MoleculeGPT model
(https://ai4d3.github.io/papers/34.pdf) using PyG.
(https://ai4d3.github.io/2023/papers/34.pdf) using PyG.
"""
import argparse
import math
Expand Down
2 changes: 1 addition & 1 deletion torch_geometric/llm/models/molecule_gpt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ def pad_or_truncate(embeddings: Tensor, max_seq_len: int,
class MoleculeGPT(torch.nn.Module):
r"""The MoleculeGPT model from the `"MoleculeGPT: Instruction
Following Large Language Models for Molecular Property Prediction"
<https://ai4d3.github.io/papers/34.pdf>`_ paper.
<https://ai4d3.github.io/2023/papers/34.pdf>`_ paper.

Args:
llm (LLM): The LLM to use.
Expand Down
2 changes: 1 addition & 1 deletion torch_geometric/llm/models/protein_mpnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ def message(self, x_i: torch.Tensor, x_j: torch.Tensor,


class ProteinMPNN(torch.nn.Module):
r"""The ProteinMPNN model from the `"Robust deep learning--based
r"""The ProteinMPNN model from the `"Robust deep learning based
protein sequence design using ProteinMPNN"
<https://www.biorxiv.org/content/10.1101/2022.06.03.494563v1>`_ paper.

Expand Down
4 changes: 2 additions & 2 deletions torch_geometric/nn/conv/fused_gat_conv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,8 @@ class FusedGATConv(GATConv): # pragma: no cover
r"""The fused graph attention operator from the
`"Understanding GNN Computational Graph: A Coordinated Computation, IO, and
Memory Perspective"
<https://proceedings.mlsys.org/paper/2022/file/
9a1158154dfa42caddbd0694a4e9bdc8-Paper.pdf>`_ paper.
<https://proceedings.mlsys.org/paper_files/paper/2022/file/
b559156047e50cf316207249d0b5a6c5-Paper.pdf>`_ paper.

:class:`FusedGATConv` is an optimized version of
:class:`~torch_geometric.nn.conv.GATConv` based on the :obj:`dgNN` package
Expand Down