Comments (1)
Hi,
Thanks for pointing out this. Right, handling the graph data by using the NetworkX graph object seems not efficient. But the performance issue for generating the HeteroGraph
might be mainly caused by what DeepSNAP does internally, transforming the NetworkX graph into tensors and in the link prediction case it will also split multiple negative edges. These can actually cause the performance / memory issue. One potential solution is to not use DeepSNAP if you don't need to manipulate the graph heavily (for example during training). You can use PyG directly with its transforms functions. Also, now the heterogeneous functionality has also been merged into the PyG and you can use it from PyG directly. If you have heavy graph manipulation requirements and need to use the graph algorithm from NetworkX, you can try to feed tensors directly such as this example but I am not sure whether this can work for the link prediction task (also not very sure about the performance). I will benchmark and try to find the performance issue if I have time recently.
Thanks.
from deepsnap.
Related Issues (20)
- Using the ogbl-biokg with DeepSNAP HOT 4
- Negative sampling in HeteroGraph
- How to split a heterogeneous graph for link_pred targeting specific edge_type? HOT 2
- CUDA out of memory
- Difference between edge_index and edge_label_index HOT 2
- Error in num_nodes
- Heterogeneous link prediction with inductive split
- How to convert PyG heterograph to DeepSnap heterograph?
- How to convert pyTorch-Geometric custom datasets into DeepSnap datasets? HOT 1
- Deepsnap doesnt have neighbor sampler? HOT 1
- Inductive Link Prediction graph copying
- How to generate WN18.gpickle or How to format own KGs
- proposal
- Slow dataloading due to NetworkX graph being collated
- Some questions of Examples/subgraph_matching
- Converting PyG 2.4.0 dataset to a list of deepsnap graphs no longer works! HOT 3
- Hi,I was tring to transfer my deepsnap HeteroGraph object into a pytorch_geometric HeteroData Object, I wonder if there is any easy path to do it?
- Converting deepsnap HeteroGraph object into a pytorch_geometric HeteroData Object
- Explanation of forward_op in deepsnap.hetero_gnn
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepsnap.