StellarGraph - Machine Learning on Graphs
Fixed bugs:
Fixed bugs:
We are excited to announce the 0.8.0
release of the library. This release extends stellargraph
by adding new algorithms and demos, enhancing interpretability via saliency maps for GAT, and further simplifying graph ML workflows through standardised model APIs and arguments. More details on new features and enhancements are listed below.
New algorithms:
Implemented enhancements:
build()
method to GCN and GAT classes #439
activations
argument to GraphSAGE and HinSAGE classes #381
Refactoring:
keras
to use tensorflow.keras
#471
flatten_output
arguments for all models #447
Fixed bugs:
Ensemble.fit_generator()
argument #461
Limited NetworkX version to <2.4 and Tensorflow version to <1.15 in installation requirements, to avoid errors due to API changes in the recent versions of NetworkX and Tensorflow.
Limited Keras version to <2.2.5 and Tensorflow version to <2.0 in installation requirements, to avoid errors due to API changes in the recent versions of Keras and Tensorflow.
Fixed bugs:
demos
requirements in setup.py
. Python-igraph doesn't install on many systems and is only required for the clustering notebook. See the README.md
in that directory for requirements and installation directions.New features and enhancements:
Refactoring:
FullBatchNodeGenerator
to accept simpler method
and transform
arguments #405
Fixed bugs:
Fixed bugs:
func_opt
function in FullBatchNodeGenerator
classdemos/node-classification/gcn/gcn-cora-example.py:144
: incorrect argument was used to pass
the optional function to the generator for GCNEnhancements:
gcn
and gat
models in demos/ensembles/ensemble-node-classification-example.ipynb
New features and enhancements:
Fixed bugs: