skeleton for LR encoding ED model with extension of estimator

[davidsebfischer]

Added estimators that yield neighbrouhood tensors of features and avoid using the full adjacency matrix, this can be used for single layer embeddings and breaks the scaling of attention coefficient computation with number of nodes in graph.

The core design feature of the models contributed here is that the models receive two feature input tensors (batch, target nodes, features), (batch, target nodes, neighbors, features), where neighbors is padded to be constant (the max neighborhood size in data set). The adjacency matrix is then just a padding indicator (batch, target nodes, neighbors). For neighbors << max nodes this can result in desirable reduction in data communitcation to GPU and desirable intermediate tensor sizes before masking is applied via the adjacenc matrix, e.g. for attention. This only works fo rmodels with a single graph embedding layer. This implementation can be kept in parallel to the more general implementation that we already have. I recreated the Max and Gcn model layers for this type of input.

• extract gene names in estimator .set_input_features
• enable extraction of LR-pairwise activations (embedding) and relate to output weights in linear decoder setting.
• add unit test for new models

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB