-
Notifications
You must be signed in to change notification settings - Fork 360
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.
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
First commit for heterogeneous graph support #125
First commit for heterogeneous graph support #125
Conversation
This includes: - a new data-structure 'StaticHeteroGraphTemporalSignal' that works like 'StaticGraphTemporalSignal' but with troch_geometric HeteroData objects as snapshots; instead of np arrays, dictionaries wirth key(node/edge types as strings)/value(indices/features as np arrays) are expected - code tests for the new data-structure - documentation for the new data-structure
Hi there @doGregor , it seems to depend on a version of PyG that already has the hetero data module. When was that introduced? Which version? |
Hi @benedekrozemberczki , heterogeneous graphs have been introduced in PyG version 2.0.0 that was released on september 13 2021 |
The 0.5.0 support PyG 2.0 please update the PR and let us go from there @doGregor ! |
Great, thank you! Updated it. |
This includes: - a new data structure, that represents PyG HeteroDataBatch snapshots for static heterogeneous graphs with temporal signals - documentation - tests
Codecov Report
@@ Coverage Diff @@
## master #125 +/- ##
==========================================
- Coverage 99.16% 98.11% -1.05%
==========================================
Files 48 50 +2
Lines 3829 4041 +212
==========================================
+ Hits 3797 3965 +168
- Misses 32 76 +44
Continue to review full report at Codecov.
|
I would suggest increasing the test coverage first. |
edge tests edge index tests additional attributes None test
edge test edge weights test additional attributes None test batch assigned test
- new data structure that works like DynamicGraphStaticSignal but with PyG HeteroData objects - tests - documentation
- data structure that works like DynamicGraphStaticSignal but with PyG HeteroData Batches - tests - documentation
- new data structure that works like DynamicGraphTemporalSignal but with PyG HeteroData objects - tests -documentation
- data structure that works like DynamicGraphTemporalSignalBatch but with PyG HeteroData Batches instead - tests -documentation
Is this ready for review @doGregor ? |
Hi @benedekrozemberczki , yes, the new data structures are ready to review. What's left afterwards is updating the train/test split method and finally the layers. Will go on with that soon... |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
These are really cool things.
Merged these for now! |
This includes:
StaticHeteroGraphTemporalSignal
that works likeStaticGraphTemporalSignal
but withtorch_geometric
HeteroData
objects as snapshots; instead of np arrays, dictionaries wirth key(node/edge types as strings)/value(indices/features as np arrays) are expectedFeedback is welcome! If you think it makes sense to extend your package like that it would be great to open a new branch for heterogeneous support where we can go on working in this direction.
Thanks and cheers, Gregor