-
Need to implement the REINFORCE algorithm to train the GNN.
-
**Submitting author:** @asogaard (Andreas Søgaard)
**Repository:** https://github.com/graphnet-team/graphnet
**Branch with paper.md** (empty if default branch):
**Version:** v1.0.0
**Editor:** @dfm
*…
-
It looks like the only learnable part of your proposed algorithm is the mapping operation, the GNN model. The logical operations use fuzzy logic and do not require learning. So, why not use the traine…
-
### 🐛 Describe the bug
Hi there,
I tried to calculate fidelity for the GNNExplainer example (https://github.com/pyg-team/pytorch_geometric/blob/master/examples/gnn_explainer.py). In doing that, …
-
### 🐛 Describe the bug
I trained a GCN model on Goggle collab for multi-class classification and was trying to get explanations for the edge values using the PGExplainer. All the code runs well whi…
-
Hi, thanks for sharing the code.
I noticed that you used `self.mlp` to work on pairs of node representations to obtain the edge scores. Then this edge score is used to select the edges of the causa…
-
### 🚀 The feature, motivation and pitch
I am working with heterogeneous knowledge graphs and am trying to do link prediction on them. The specific issue I am facing is that I cannot find any workin…
-
## ❓ Questions & Help
Hi Matthias, I'm wondering if there's a way to apply functions (or algorithms) to each batch in an efficient manner? In my case, I wish to apply an algorithm that takes in r…
-
Edward Ma. [Random Walk in Node Embeddings (DeepWalk, node2vec, LINE, and GraphSAGE)](https://pub.towardsai.net/random-walk-in-node-embeddings-deepwalk-node2vec-line-and-graphsage-ca23df60e493).
-
- How to balance DNN computation on GPU and sampling compuation on cpu in graph-learn, if GPU is fast and data provided by CPU sampling is not fast enough? Generally, We will use latency hidden sk…