neat-ml

neat-ml copied to clipboard

We have some existing implementations but will need to allow access to them through a NEAT config.

caufieldjh

Not every run will involve starting from scratch on a graph, but NEAT currently expects a `graph_data` block to be present in the config. Omit it, and a KeyError is...

caufieldjh

Display errors to users at conclusion of NEAT run

1

NEAT runs may encounter a variety of caught errors and warnings: * For sklearn: https://scikit-learn.org/stable/modules/classes.html#module-sklearn.exceptions * For TF: https://www.tensorflow.org/api_docs/python/tf/errors These should be presented to the user, perhaps through a ERROR.txt...

caufieldjh

Replace NEATs BERT text embedding stuff with Ensmallen's (better) version of this

1

Right now we are including BERT embeddings for textual elements in the graph in NEAT using a fairly naive average embedding of all text for a given node. Ensmallen now...

justaddcoffee

Per conversation in BBOP Deep Dive, we could considering using model cards as described [in this Mitchell et al paper](https://arxiv.org/abs/1810.03993) to describe and benchmark trained ML models This likely should/could...

justaddcoffee

Create index.html upon uploading new output

2

Newly created output from NEAT is uploaded to a remote location (i.e., S3 bucket) but isn't inherently navigable because it does not have an index.html written. We will need to...

caufieldjh

@caufieldjh could flesh this ticket out to do KG-IDG link prediction as discussed [here](https://github.com/Knowledge-Graph-Hub/kg-idg/issues/43)

justaddcoffee

Providing NEAT with a config file where node and/or edge do not resolve to a TSV currently throws a `ValueError` (i.e., if it's a tar.gz). This could be more informative...

caufieldjh

Fix tensorflow and disable bert

1

justaddcoffee

Code to produce holdouts from Ensmallen

2

to address #16

justaddcoffee