Leveraging Graphs for Artificial Intelligence and Machine Learning - Phani Dathar

neo4j 59 views 18 slides May 09, 2023
Slide 1
Slide 1 of 18
Slide 1
1
Slide 2
2
Slide 3
3
Slide 4
4
Slide 5
5
Slide 6
6
Slide 7
7
Slide 8
8
Slide 9
9
Slide 10
10
Slide 11
11
Slide 12
12
Slide 13
13
Slide 14
14
Slide 15
15
Slide 16
16
Slide 17
17
Slide 18
18

About This Presentation

Relationships are highly predictive of behavior. Graph technology abstracts connections in our data so businesses can apply relationships and network structures to make better predictions. Hear about the journey from graph analytics and machine learning to graph-enhanced AI. We’ll also cover how e...


Slide Content

© 2023 Neo4j, Inc. All rights reserved.1
Leveraging Graphs for
Artificial Intelligence and
Machine Learning
Phani Dathar, PhD
Director, Graph Data Science
[email protected]

© 2023 Neo4j, Inc. All rights reserved.
Knowledge GraphsGraph Feature
Engineering and
Graph ML
Graph Analytics,
Investigations and
Counterfactuals
Integrations and
Knowledge Graphs
for Heuristic AI
CapitalizeAnalysis DataModeling
Neo4jNeo4j GDSNeo4j BloomNeo4j Connectors
GRAPHS ENRICH ALL PHASES OF AI ECOSYSTEM

© 2023 Neo4j, Inc. All rights reserved.
KNOWLEDGE GRAPHS
Knowledge graphs
provide deep,
dynamic context.
Connecting data
adds context and
improves outcomes.

© 2023 Neo4j, Inc. All rights reserved.
VENDORS AND
SUPPLIERSOPERATIONSLOGISTICSSALES &
MARKETING
Bill Of MaterialsSupply ChainCustomer 360
VALUE CHAIN: ORGANIZATIONAL KNOWLEDGE GRAPH

© 2023 Neo4j, Inc. All rights reserved.
Knowledge GraphsGraph Feature
Engineering and
Graph ML
Graph Analytics,
Investigations and
Counterfactuals
Integrations and
Knowledge Graphs
for Heuristic AI
CapitalizeAnalysis DataModeling
GRAPH DATA SCIENCE
Neo4jNeo4j GDSNeo4j BloomNeo4j Connectors

© 2023 Neo4j, Inc. All rights reserved.7
KNOWLEDGE GRAPHS TO GRAPH MACHINE LEARNING
Knowledge Graphs Graph Algorithms Graph Native ML
Find the patterns you’re
looking for in connected data
Identify associations,
anomalies, and trends using
unsupervised machine learning
Learn features in your graph
that you don’t even know
are important yet

© 2023 Neo4j, Inc. All rights reserved.
WHAT ARE GRAPH ALGORITHMS?

© 2023 Neo4j, Inc. All rights reserved.
INSIGHTS FROM GRAPH ALGORITHMS
Outliers, Influencers, Vulnerabilities,..
Recommendations, Homophily, Outliers,..
Recommendations, What-if Analysis, Disambiguation,..
Dimensionality Reduction, Representation Learning, ..
Shortest Path, Optimal path, Route Optimization,...
Link prediction, Recommendations, Next-Best Action,..
Centrality
Pathfinding
Community
Detection
Similarity
Embeddings
Link Prediction

© 2023 Neo4j, Inc. All rights reserved.
IDENTITY MANAGEMENT/ ENTITY RESOLUTION
Graph algorithms and graph embeddings are used for generating
context and resolving identities/entities
Neo4j APOC
Capture relationships between
entities across data sources
using a knowledge graph
Create additional
weighted relationships
based on similar text
description and/or other
similar metadata
Construct node
embeddings and
resolve entities based
on weighted pairwise
similarity between
various entities
Identify communities
of entities based on
distance between
node embeddings

© 2023 Neo4j, Inc. All rights reserved.
GRAPH ENRICHED ML WORKFLOWS
Graph-Native
Feature
Engineering
Train
Predictive Model
Queries
Algorithms
Embeddings
1.Model Type
2.Property
Selection
3.Train & Test
4.Model
Selection
Apply Model to
Existing / New
Data
Use Predictions
for Decisions
Use Predictions
to Enhance
the Graph
Publish & ShareStore Model in
Database

© 2023 Neo4j, Inc. All rights reserved.
GRAPH FEATURE ENGINEERING
Human-crafted query, human-readable result
MATCH (p1:Person)-[:ENEMY]->(:Person)<-[:ENEMY]-(p2:PERSON)
MERGE (p1)-[:FRIEND]->(p2)
AI-learned formula, machine-readable result
Predefined formula, human-readable result
PageRank(Emil) = 13.25
PageRank(Amy) = 4.83
PageRank(Alicia) = 4.75
Node2Vec(Emil) =[5.4 5.1 2.4 4.5 3.1]
Node2Vec(Amy) =[2.8 1.8 7.2 0.9 3.0]
Node2Vec(Alicia)=[1.4 5.2 4.4 3.9 3.2]
Queries
Algorithms
Embeddings
Machine
Learning
Workflows
Train ML models
based on results

© 2023 Neo4j, Inc. All rights reserved.
NEO4J GDS: IMPROVE MODELS AND ANSWER BIG QUESTIONS
13
Pathfinding
& Search
CentralityCommunity
Detection
Machine
Learning
Link
Prediction
SimilarityEmbeddingsAnd more …
Over 65 pretuned, parallelized algorithms.Iterate fast with different data sets, models,
and version trained models.
Bring the context of your connected data
into a format that other pipelines can
ingest.
The Largest Catalog of
Graph Algorithms
Native Graph Catalog and
Analytics Workspace
Graph Embeddings for
Machine Learning

© 2023 Neo4j, Inc. All rights reserved.
Knowledge GraphsGraph Feature
Engineering and
Graph ML
Graph Analytics,
Investigations and
Counterfactuals
Integrations and
Knowledge Graphs
for Heuristic AI
CapitalizeAnalysis DataModeling
Graphs Enrich All Phases of Decision Making
Neo4jNeo4j GDSNeo4j BloomNeo4j Connectors

© 2023 Neo4j, Inc. All rights reserved.
NEO4J BLOOM: GRAPH VISUALIZATION

© 2023 Neo4j, Inc. All rights reserved.
NEO4J CONNECTORS: OPERATIONALIZE GDS WORKFLOWS

© 2023 Neo4j, Inc. All rights reserved.17
Demo: Claims Investigation
with Graph Data Science

© 2023 Neo4j, Inc. All rights reserved.
CLAIMS INVESTIGATION
Explore Claims
Data by
visualization
Generate
hypothesis /
theories
Insights from
connected data
Graph algorithms to
generate topological
features
ML models with
graph features
1
2
3
4
5

© 2023 Neo4j, Inc. All rights reserved.
NEO4J:FOR APPLICATIONS ANDANALYTICS
Graph Transactions,
Storage & Querying Graph Analytics, ML,
& Data Science
Intelligent ApplicationsBetter Predictions
Tags