graphlet

graphlet copied to clipboard

# Use of `graphlet.nlp.ie` The entities and their relations that form the input to this module will be extracted using `graphlet.nlp.ie` - see #11 and #1. # Integration with BLINK...

rjurney

# Use of `graphlet.etl` Schema Models We can use `graphlet.etl`'s [Pandera Schema Models](https://pandera.readthedocs.io/en/latest/schema_models.html) schema models to define the entities and relations we are extracting. ## About `graphlet.etl` The module `graphlet.etl`...

rjurney

# Create a generic, configurable system for entity resolution of heterogeneous networks using pre-trained LMs and GATs Graph Neural Networks (GNNs) accept arbitrary features as input... making an embedding produced...

rjurney

Incorporate spark-rapids into architecture

1

[spark-rapids](https://nvidia.github.io/spark-rapids/) incorporates [RAPIDS](https://rapids.ai/) into [Apache Spark](https://spark.apache.org/) and could accelerate our architecture significantly. * [Getting Started](https://nvidia.github.io/spark-rapids/Getting-Started/) makes this sound easy. * [spark-rapids on Databricks](https://nvidia.github.io/spark-rapids/docs/get-started/getting-started-databricks.html)

rjurney

# Summary This ticket is to create utilities - including node and edge base classes - that provide an object-oriented interface with runtime validation for defining data types in a...

rjurney

Implement efficient random motif searching via neural subgraph matching

3

Motif search for heterogeneous networks - especially temporal heterogeneous networks - has fundamental scalability challenges. [Neural Subgraph Matching](https://arxiv.org/abs/2007.03092) proposes a technique using graph representation learning and vector search called _NeuroMatch_....

rjurney

In order to determine whether a graphlet is a network motif, we need to compare its frequency versus a null model to determine if it is statistically significant. This means...

rjurney

# PySpark / GraphFrames  # Property Graph Minors 

rjurney