G-retriever (GNN+LLM) example w/ demo

CHANGELOG.md

@@ -7,6 +7,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 
 ### Added
 
+- Added the `WebQSPDataset` dataset with example training G-Retriever (GNN+LLM) ([#8984](https://github.com/pyg-team/pytorch_geometric/pull/8984))
 - Added support for `EdgeIndex` in `message_and_aggregate` ([#9131](https://github.com/pyg-team/pytorch_geometric/pull/9131))
 - Added `CornellTemporalHyperGraphDataset` ([#9090](https://github.com/pyg-team/pytorch_geometric/pull/9090))
 - Added support for cuGraph data loading and `GAT` in single node Papers100m examples ([#8173](https://github.com/pyg-team/pytorch_geometric/pull/8173))

examples/README.md

@@ -14,8 +14,10 @@ For examples on [Open Graph Benchmark](https://ogb.stanford.edu/) datasets, see
 - [`ogbn_papers_100m.py`](./ogbn_papers_100m.py) is an example for training a GNN on the large-scale `ogbn-papers100m` dataset, containing approximately ~1.6B edges.
 - [`ogbn_papers_100m_cugraph.py`](./ogbn_papers_100m_cugraph.py) shows how to accelerate the `ogbn-papers100m` workflow using [CuGraph](https://github.com/rapidsai/cugraph).
 
-For examples on using `torch.compile`, see the examples under [`examples/compile`](./compile).
+For examples on co-training LLM with GNN, see examples and README under [`examples/llm_plus_gnn`](./llm_plus_gnn).
 
-For examples on scaling PyG up via multi-GPUs, see the examples under [`examples/multi_gpu`](./multi_gpu).
+For examples on using `torch.compile`, see examples and README under [`examples/compile`](./compile).
 
-For examples on working with heterogeneous data, see the examples under [`examples/hetero`](./hetero).
+For examples on scaling PyG up via multi-GPUs, see examples and README under [`examples/multi_gpu`](./multi_gpu).
+
+For examples on working with heterogeneous data, see examples and README under [`examples/hetero`](./hetero).

examples/llm_plus_gnn/README.md

@@ -0,0 +1,5 @@
+# Examples for LLM and GNN co-training
+
+| Example                              | Description                                                                                                                                             |
+| ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [`g_retriever.py`](./g_retriever.py) | Example for Retriever Augmented Generation (RAG) w/ GNN+LLM by co-training LLAMA2 with GAT for answering questions based on knowledge graph information |