Comments (4)
After thinking more about subgraph training, I don't feel that we need to support the "shared" mode for subgraph training. After the forward computation in a mini-batch, we don't need to write data back to the parent frame directly. Users should explicitly write data back with "inplace=True" to avoid index_copy. In addition, does any underlying framework support non-contiguous view on a tensor?
from dgl.
I think it's still good to have for completeness, but you could put it in a lower priority and may not finish it in one PR. I agree that we need an "inplace=True" flag when writing back. I don't think current framework support such view. That's why we have FrameRef for that.
from dgl.
OK. let's postpone the implementation of the "shared" mode until we find a real application for this.
from dgl.
The basic "non-shared" mode has been done in #90. We are now focusing on performance issue.
from dgl.
Related Issues (20)
- [GraphBolt] sample_neighbors() with prob/mask is 14x slower than w/o prob/mask HOT 1
- [Dist] test_mp_dataloader::test_dist_dataloader seg fault occasionally HOT 2
- DGL not work with numpy >= 2.0 HOT 5
- [dev] add command line interface for common utility functions HOT 1
- [doc] doc build failed
- maybe a potential bug of neighbor sampling of distributed dgl heterogeneous graph HOT 2
- Only CPU versions can be installed by commands in the `Get Started` page with options `Windows` + `CUDA` selected. HOT 2
- DGL built from source in Windows 11 (CUDA 12.1, PyTorch 2.3.0): Cannot find DGL C++ graphbolt library. HOT 3
- [CI] Spurious test failures HOT 6
- [GraphBolt] FutureWarning in ondisk_dataset
- Structure S3-Hosted Wheels as PyPI Repository HOT 9
- Issue with prob_name in graphbolt neighbor sampling HOT 9
- heterograph.set_batch_num_edges could run automatically if batch_num_nodes is set
- [GraphBolt][CUDA] Refactor TemporalNeighborSamplerImpl
- [GraphBolt] Temporal link prediction example crash HOT 4
- Edge explanations using dgl.nn.pytorch.explain.GNNExplainer HOT 1
- Building dgl from source completely without pytorch HOT 6
- AttributeError: '_OpNamespace' 'graphbolt' object has no attribute 'set_max_uva_threads' HOT 2
- [GraphBolt] ogbn-arxiv accuracy values are lower than expected. HOT 10
- Code running for distributed graph training HOT 2
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 dgl.