|Neo4j Announces Graph Machine Learning Framework|
|Written by Kay Ewbank|
|Tuesday, 27 October 2020|
Neo4j has announced a graph machine learning framework that the developers describe as making advanced graph-based machine learning techniques more accessible.
The framework is included in the latest Neo4j version, and consists of graph embedding algorithms that learn the structure of your graphs rather than relying on predetermined formulas to calculate specific features like centrality scores.
Neo4j database is one of the most popular graph databases. It stores data and relationships in graph structures, and is highly scalable. Developers can build intelligent applications that traverse s large, interconnected datasets in real time. It has a native graph storage and processing engine, and a graphical query language.
The new addition calculates the shape of the surrounding network for each piece of data inside of a graph, enabling far better machine learning predictions. The developers say the ability to learn generalized, predictive features from data is significant because organizations don't always know how to represent connected data for use in machine learning models.
The graph embedding algorithms sample the topology and properties of the graph and then reduce its complexity to just those significant features for further machine learning. The algorithms can also eliminate plateaus by abstracting the structure of a graph using its topology and properties, so can predict outcomes based on the connections between data points – rather than raw data alone.
The developers say the framework makes it faster to carry out feature engineering on data by limiting algorithms are used for testing when predictive features are ambiguous and using high-performance methods like FastRP.
Once the algorithms have learned the model, the functions that have learned can be stored in GraphSage,then applied to new data for new embeddings and predictions – without having to retrain your model. You can also add ongoing scoring and classification results, as well as predicting missing information for better insights.
Neo4j for Graph Data Science version 1.4 includes three new graph embedding options that learn graph topology to calculate more accurate representations. Node2Vec is a well-known graph embedding algorithm which uses neural networks; FastRP is a graph embedding up to 75,000 times faster than node2Vec, while providing equivalent accuracy and scaling well even for very large graphs; and GraphSAGE is an embedding algorithm and process for inductive representation learning on graphs that uses graph convolutional neural networks and can be applied continuously as the graph updates.
The new version of Neo4j for Graph Data Science also adds general machine learning algorithms such as the k-nearest neighbors algorithm (k-NN), commonly used for pattern-based classification, to make it easier to gain insights from graph embeddings.
or email your comment to: firstname.lastname@example.org
|Last Updated ( Tuesday, 27 October 2020 )|