Tensorflow-gnn

**Full Changelog**: https://github.com/tensorflow/gnn/compare/v0.4.0rc2...v0.4.0

Bugfix for python 3.7 compatibility

**Full Changelog**: https://github.com/tensorflow/gnn/compare/v0.4.0rc1...v0.4.0rc2

Removes explicit requirement for google-vizier to stay compatible with google Colab.

**Full Changelog**: https://github.com/tensorflow/gnn/compare/v0.4.0rc0...v0.4.0rc1

What's Changed
* Expose `tfgnn.dataset_from_generator` helper. by copybara-service in https://github.com/tensorflow/gnn/pull/115
* Add triple converter for RDF-style input. by copybara-service in https://github.com/tensorflow/gnn/pull/119
* Doc fix: The the intro page describes GNNs in some generality. by copybara-service in https://github.com/tensorflow/gnn/pull/123
* Enables disabled runner tests from RNG changes in Keras by copybara-service in https://github.com/tensorflow/gnn/pull/122
* Fixes error with named features in `homogeneous` constructor by copybara-service in https://github.com/tensorflow/gnn/pull/121
* Let DatasetProviders raise FileNotFoundError if no files match pattern. by copybara-service in https://github.com/tensorflow/gnn/pull/139
* Helper function for random reordering within segment ids. by copybara-service in https://github.com/tensorflow/gnn/pull/135
* Updates Bazel dep to 2.8.0. by copybara-service in https://github.com/tensorflow/gnn/pull/150
* In a GraphTensor guide example, add `tf.constant(...)` to clarify by copybara-service in https://github.com/tensorflow/gnn/pull/162
* Shorten function name `to_sampling_spec` to `build`, maintaining backward-compatibility. by copybara-service in https://github.com/tensorflow/gnn/pull/159
* Add streaming API to read Unigraph artifacts (node sets, edge sets) as iterables. by copybara-service in https://github.com/tensorflow/gnn/pull/166
* Unsupervised (i.e.: model generated target vs. dataset generated label) refactors. by copybara-service in https://github.com/tensorflow/gnn/pull/165
* Check checkpoint_options.checkpoint_dir: it may be unfilled in a caller's checkpoint_options. by copybara-service in https://github.com/tensorflow/gnn/pull/172
* Multitask refactors. by copybara-service in https://github.com/tensorflow/gnn/pull/181
* s/class_id/sparse_class_id/g by copybara-service in https://github.com/tensorflow/gnn/pull/189
* Make runner/examples/ogbn/mag/train.py parametric in the GNN model type. by copybara-service in https://github.com/tensorflow/gnn/pull/191
* Fix typo. by copybara-service in https://github.com/tensorflow/gnn/pull/192
* Use strings to set BQ read method. by copybara-service in https://github.com/tensorflow/gnn/pull/199
* Fix a typo/ by copybara-service in https://github.com/tensorflow/gnn/pull/206
* Local tf import to avoid global session. by copybara-service in https://github.com/tensorflow/gnn/pull/208


**Full Changelog**: https://github.com/tensorflow/gnn/compare/v0.3.0...v0.4.0rc0

What's Changed
* An initial version of transformer-style multi-head attention. in https://github.com/tensorflow/gnn/pull/55
* Add TPUStrategy support to the runner. in https://github.com/tensorflow/gnn/pull/51
* Add a keys variant for transformer-style multi-head attention. in https://github.com/tensorflow/gnn/pull/56
* Enable dataflow prime and add edge_aggregation_method choice to example. in https://github.com/tensorflow/gnn/pull/68
* Fix typos in gnn_modelling.md by dgoekmen in https://github.com/tensorflow/gnn/pull/70
* In type spec deserialization, ensure class DType in https://github.com/tensorflow/gnn/pull/83
* Integer mathematics (i.e., TPU-friendly) for adding self-loops on GraphTensors. in https://github.com/tensorflow/gnn/pull/75
* Export symbol tfgnn.is_ragged_tensor(). in https://github.com/tensorflow/gnn/pull/87
* Add per-class metrics for multi-class classification. in https://github.com/tensorflow/gnn/pull/81
* Initial support for graph pieces shapes relaxation (nodes and edges). Helper function to easy dataset creation from scalar graph pieces generator. in https://github.com/tensorflow/gnn/pull/84
* Adds tfgnn.keras.layers.AddSelfLoops in https://github.com/tensorflow/gnn/pull/86
* Remove tfgnn.keras.layers.TotalSize in favor of .total_size and in https://github.com/tensorflow/gnn/pull/96
* Improve the error message when num_classes and class_names are both None. in https://github.com/tensorflow/gnn/pull/99
* Compute SizeConstraints for TPU padding before calling distribute_datasets_from_function. in https://github.com/tensorflow/gnn/pull/77
* Builder pattern for `SamplingSpec` proto. in https://github.com/tensorflow/gnn/pull/104
* Ensure that L2 regularization for GCN is correctly [de]serialized. in https://github.com/tensorflow/gnn/pull/105
* Pin google-api-core version due to protobuf v4.21.0 tensorflow incompatibility. in https://github.com/tensorflow/gnn/pull/109

New Contributors
* dgoekmen made their first contribution in https://github.com/tensorflow/gnn/pull/70

**Full Changelog**: https://github.com/tensorflow/gnn/compare/v0.2.0.dev1...v0.3.0

Removes GCP dependencies from setup.py and updates apache-beam.

**Full Changelog**: https://github.com/tensorflow/gnn/compare/v0.2.0...v0.2.1