Data Day Texas: Graph Convolutional Networks For Node Classification

A method of classifying nodes in an information network by application of a non-Euclidean convolutional neural network

Contact us

Data Day Texas: Graph Convolutional Networks For Node Classification

A method of classifying nodes in an information network by application of a non-Euclidean convolutional neural network

Fill out form to continue
All fields required.
Enter your info once to access all resources.
By submitting this form, you agree to Expero’s Privacy Policy.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Steve describes a method of classifying nodes in an information network by application of a non-Euclidean convolutional neural network. The convolutional layers are kerneled to operate directly on the natural manifold of the information space, and thus produce output more accurate than analysis on information arbitrarily embedded in a Euclidean geometry. First, Steve describes the benefits of operating in a non-Euclidean geometry. He then sketches out how graph convolutional networks work. Finally, Steve demonstrates the application of this technique by predicting the credit-worthiness of applicants based on their population characteristics and their relationships to other individuals.

User Audience

Services & capabilities

Project Details

Technologies

January 27, 2018

Data Day Texas: Graph Convolutional Networks For Node Classification

A method of classifying nodes in an information network by application of a non-Euclidean convolutional neural network

Tags:

Steve describes a method of classifying nodes in an information network by application of a non-Euclidean convolutional neural network. The convolutional layers are kerneled to operate directly on the natural manifold of the information space, and thus produce output more accurate than analysis on information arbitrarily embedded in a Euclidean geometry. First, Steve describes the benefits of operating in a non-Euclidean geometry. He then sketches out how graph convolutional networks work. Finally, Steve demonstrates the application of this technique by predicting the credit-worthiness of applicants based on their population characteristics and their relationships to other individuals.

User Audience

Services

Project Details

Similar Resources

Expero CoNNected Financial Crimes

Recent events have created increased focus on Financial Crimes attacks as well as Cyber, AML, and fraud attacks that are growing in sophistication creating losses in the billions. This session will identify how to reduce false positives by 60%, increase accuracy by 70% and improve overall team productivity by 80% with Expero CoNNected software that bolts onto current on premise technology.

Watch Demo

A Fraud Series - Part Two: Adapting Technology to Fight Fraud

This post looks at the different technology approaches and adaptations to finding and detecting fraud, and the technology behind Expero's Fraud Product.

Watch Demo

Fight Fraud With Graph + ML

During this webinar, TigerGraph and Expero will discuss the complexity and state of AML, and how the roles of Humans, Graph, and Machine Learning combine.

Watch Demo

Fight Cyber Crime and Fraud With Graph & ML

During this webinar, TigerGraph and Expero will discuss how to visualize cyber threat information using Graph & ML, and how new technology can help Financial Services team fight cyber fraud.

Watch Demo