March 7th - 11th Weekly Updates: TigerGraph Machine Learning Workbench, Blogs, Latest Videos, and More!

Hello @TigerGraph_Community!

Here’s your weekly round-up of updates, including the release of TigerGraph Machine Learning Workbench, blogs, videos, and more!

weekly_update_header

:hammer_and_wrench: TigerGraph Machine Learning Workbench is here!

We’re excited to announce that our TigerGraph Machine Learning Workbench is now available!
TigerGraph ML Workbench is a Jupiter-based Python framework that allows you to develop AI and Machine Learning models on top of a TigerGraph solution. With TigerGraph ML Workbench, you can now easily explore the potentials of Graph Neural Networks for your domains!

Success Stories of Graph Neural Networks

GNN has proven its success both in academic and industrial settings. It tends to outperform other traditional machine learning techniques when there are well-defined relationships between data as it directly models the connectivities of graph data. Listed below are some references on how GNN models are transforming a wide range of applications and industries to spark new ideas on how much more we can do for our customers.

  • Recommendation Engine
    Pinterest introduced PinSAGE [1], an architecture that can serve real-time recommendations to their users, resulting in a 10-30% improvement compared to other deep learning methods when evaluated in A/B testing.

  • Supply Chain
    Amazon released a GNN architecture [2] that incorporates temporal information with GNNs for demand forecasting. The method models interactions between products and sellers on Amazon in a graph, resulting in a 16% improvement over other state-of-the-art forecasting methods.

  • Healthcare
    AstraZeneca has used graph neural networks like GraphSAGE to generate knowledge graph embeddings for predicting possible drug-drug interactions such as potential synergies between drugs, as well as possible polypharmacy side effects [3]. Additionally, the possibility of repurposing drugs to treat COVID has been studied using a drug repurposing knowledge graph and GNNs [4].

  • Financial Institutions
    GCNs have been studied for predicting money-laundering behavior in Bitcoin transaction networks and have been shown to perform admirably compared to other approaches [5].

TigerGraph Machine Learning Workbench Quick Start Instructions:

Whether you are new to TigerGraph or are a current user, we have a path to get you started quickly.

  • (Option 1) ML Workbench Sandbox - This Docker image includes the TigerGraph database with data set preloaded, ML Workbench preconfigured, and example GNN notebooks written in python to kick start your GNN development. This is the quickest way to play around with ML Workbench.

  • (Option 2) ML Workbench Standalone - If you already have a TigerGraph database instance set up and want to develop GNNs with your data set, you can download this standalone image and connect ML Workbench to your TigerGraph server. This image also comes with example GNN notebooks written in python as a template recipe.

  • (Option 3) ML Workbench for existing Jupyter Server - If you already have a TigerGraph database instance set up AND an existing notebook server running on-prem or with a third-party cloud platform such as Amazon SageMaker, you can instead download our ML Workbench python kernel.

TigerGraph Machine Learning Workbench Overview

TigerGraph ML Workbench Youtube Series:

Upcoming Webinar

[Wednesday, March 16th] Introducing ML Workbench: A Faster Way to Build Graph Neural Networks with TigerGraph

Attend this webinar and learn about:

  1. Overview of GNN, its applications, and benefits
  2. Demo of ML Workbench

:writing_hand: Latest Blogs

Powering a New Class of Member-centric Analytics and Customer Experience for Health Insurers

Preventing Audit Log Data Breaches with Data Masking and Graph Deep Link Analytics

TigerGraph Joins Dell at HIMSS 2022 for Healthcare Analytics Presentation

Part-1: Towards Conversational AI with TigerGraph + RASA + ConceptNet5

McKenzie Steenson’s, Developer Relations Intern at TigerGraph, Blog on Imposter Syndrome

:video_camera: Latest Videos

Conversational AI with TigerGraph & RASA

This video walkthrough highlights how a conceptually rich language network like ConceptNet5 can be integrated into a highly scalable TigerGraph database and how to interface conversational AI applications with TigerGraph enabling real-time in-DB querying.

TigerGraph and Applied Singularity Meetup: An Intro to Graph

In partnership with Applied Singularity Meetup Group, we’ll be exploring what graph is, how it is different from the relational databases that we’re used to, and some typical Graph use cases.

Examples will be provided as to:

  • How Graph can utilize IoT data to enable Digital Twin capabilities.
  • How to use Graph to generate deeper features for training your ML model.
  • Using Graph to combine multiple datasets for more realistic ML training.
  • How Graph is being used in production applications by some of the largest companies in the world.
  • How a Graph schema differs from that of a relational database.
  • How Graph connections make it easy to explore complex insights in your data.
  • A quiz will be given at the end.

:mega: Events

[Tuesday, March 8th] Shopping with Graphs! - Learn Rising Graph Database Technology for Full-Stack Flutter Application: Part 1
In this two-part series, we will discuss utilizing TigerGraph’s platform to showcase data relationships and application integration. Using an Amazon product reviews dataset, we will build a full-stack application with graph technology.

[Wednesday, March 9th] GSQL Schema and Query Writing Best Practices - Part 1: Schema Design Best Practices
A good graph schema design represents important relationships in a natural way, while also minimizing system resource consumption and enabling the best query performance. In this session, you will learn:

  • What to think about when defining a graph schema
  • How to define a schema that can make your query writing easy
  • How to define a schema that can accelerate your query performance
  • How to define a schema based on specific use cases

[Thursday, March 10th] Shopping with Graphs! - Learn Rising Graph Database Technology for Full-Stack Flutter Application: Part 2
In this two-part series, we will discuss utilizing TigerGraph’s platform to showcase data relationships and application integration. Using an Amazon product reviews dataset, we will build a full-stack application with graph technology.

[Tuesday, March 15th] Tampa Cybersecurity Conference
In-Person Event
As security experts in the local community continue to navigate the ever-changing landscape, you can ensure you’re on the leading edge by joining your peers at the Tampa Cybersecurity Conference. Sit alongside fellow IT and cyber executives as you hear from experts in both the public and private sectors, offering vital information on how to move your organization through the latest threats.

[Wednesday, March 16th - Thursday, March 17th] Fraud & Financial Crime USA
In-Person Event
Exploring new complexities in the fraud and financial crime landscape and best practices to stay ahead.

[Wednesday, March 23rd] GSQL Schema and Query Writing Best Practices - Part 2: GSQL Query Writing Best Practices
GSQL is a user-friendly, highly expressive, and Turing-complete graph query language. Although learning GSQL is relatively easy, it can be challenging for some users to know where to start when writing a query. In this session you will learn how to:

  • Design a traversal plan with optimal complexity
  • Make your queries memory efficient
  • Identify the performance bottleneck
  • How to choose the right accumulator
  • Learn the MPP query execution mechanisms

Office Hours - Million Dollar Challenge
Every Tuesday at 7:00 am Pacific and Thursday at 6:00 pm Pacific from February 10 to April 14th
Talk directly with our engineers every week on Discord. During our online office hours, you get answers to any questions pertaining to your Graph for All Challenge project, graph modeling, GSQL programming, and more.

  • Tuesday, March 8th - 7 am PST: Discord
  • Thursday, March 10th - 6 pm PST: Discord

:bar_chart: Trending Data Sets

Real Time Social Sentiment For Stocks & Crypto
Social Sentiment Stats for tickers/cryptos mentioned Twitter/StockTwits

Food Composition Database
Data that provide the nutritional content of foods

Toughest Sports by Skill
Top 60 Sports Ranked by Skill

:dollar: Million Dollar Challenge

We’ve got a million-dollar question: what can you do with graph? Share your graph solution for a global issue with TigerGraph, for a chance to win one of 15 cash prizes, totaling $1M!

:spiral_calendar: Mark your calendars: Submissions are due by April 20, 2022

To register and learn more, visit
Graph for All Million Dollar Challenge - TigerGraph

Join the DevPost!

1 Like