TigerGraph
ResourcesPathfinderDiscord(opens in a new tab)
ResourcesPathfinderDiscord(opens in a new tab)
Resources

Everything, In One Wall

Videos, courses, hands-on tutorials, docs, and blog posts. One place for every phase of learning.

TigerGraph
ResourcesPathfinderDiscord(opens in a new tab)

© 2026 Tiger Graph Dev Hub. All rights reserved.

  • Privacy Policy|
  • Terms of Service

Applied · 3

Clear all
  • Reference
  • Concept
  • #Graph machine learning

Levels

  • All Resources
  • Beginner
  • Intermediate
  • Advanced

Categories

  • Videos514
  • Docs644
  • Glossary50
  • Blog posts222

Assets

  • Definition36
  • Tutorial113
  • How-to guide319
  • Reference312

Tags

  • #Fraud and AML
  • #Entity resolution
  • #Recommendations
  • #GraphRAG and AI
  • #Graph machine learning
  • #Search
  • #Network analysis
  • #Performance and scale
  • #Running TigerGraph
  • #Evaluating graph

21 resources · page 1 of 2

NewestOldest
3 Col Grid2 Col GridList
Concept
BeginnerConceptApr 10, 2026

Propagation in Graphs

Propagation in graphs refers to the process of spreading status information, entity descriptions, computed values, or other data across connected entities within a network. In a graph, data is represented using nodes and edges. Nodes represent entities such as people, accounts, devices, or products. Edges represent the relationships connecting those

Code & samples
126
  • Graph Resources52
  • Concept
    109
  • Troubleshooting12
  • Security advisory4
  • Runbook
  • Article173
  • Case study26
  • Talk298
  • Release note24
  • Demo114
  • Webinar12
  • Event12
  • Report24
  • Discover
    Concept
    ConceptDec 12, 2025

    Graph Data Science

    Graph data science involves using graph algorithms, statistical techniques, and machine learning workflows to analyze data modeled as interconnected nodes and edges. Unlike flat tables, where rows are treated independently, graphs capture the structure of the domain itself—what entities exist, how they interact, and what those interactions mean. This form

    Discover
    Concept
    BeginnerConceptApr 18, 2025

    Graph Machine Learning

    Graph machine learning is a class of machine learning techniques designed specifically to learn from graph-structured data. Unlike traditional ML approaches that treat each data point as independent and flat (like a row in a table), GML captures individual entities’ attributes and the relationships between them. This allows it to

    Discover
    Reference
    Referencev1.8

    Model Trainer and Callbacks

    Train Graph Machine Learning models (such as GraphSAGE and NodePiece) in a concise way. pyTigerGraph offers built-in models that can be used with the Trainer, consuming pyTigerGraph dataloaders. Call

    Discover
    Reference
    IntermediateReferencev1.8

    Data Loaders

    Data loaders are classes in the pyTigerGraph Graph Data Science (GDS) module. You can define an instance of each data loader class through a factory function . Requires querywriters user permissions for full functi

    Discover
    Concept
    BeginnerConceptv3.10

    Node Embedding Algorithms

    Node embeddings are vector representations of properties of vertices in a graph. These vectors can be used for machine learning. The TigerGraph Graph Data Science Library provides the following node embedd

    Discover
    Concept
    IntermediateConceptv3.10

    TigerGraph Graph Data Science Library

    TigerGraph In-Database Graph Data Science (GDS) Library is a collection of more than 50 ready-to-use GSQL queries, each of which implements a standard graph or machine learning algorithm. #

    Discover
    Reference
    IntermediateReferencev3.10

    k-Means Clustering

    Supported Graph Characteristics Unweighted edges Weighted edges Directed edges Undirected edges Homogeneous vertex types Algorithm link: k-Means Clustering I

    Discover
    Reference
    AdvancedReferencev3.10

    k-Nearest Neighbors (Cross-Validation Version)

    k-Nearest Neighbors (kNN) is often used for machine learning. You can choose the value for topK based on your experience, or using cross-validation to optimize the hyperparameters.

    Discover
    Reference
    IntermediateReferencev3.10

    Fast Random Projection

    Supported Graph Characteristics Unweighted edges Directed edges Undirected edges Homogeneous vertex types Heterogeneous vertex types Algorithm link: Fast Rand

    Discover
    Reference
    IntermediateReferencev1.8

    PyTorch Geometric Transforms

    TemporalPyGTransform The TemporalPyGTransform creates a sequence of subgraph batches out of a single batch of data produced by a NeighborLoader or HGTLoader. It assumes that there are datetime attr

    Discover
    Reference
    IntermediateReferencev1.8

    Data Transforms

    There are currently two sub-modules, nodepiecetransforms , and pygtransforms . The NodePiece transforms help convert batches produced by NodePiece dataloaders into a format used by PyTorch models. The PyG transforms h

    Discover
    12