How Graphs Enhance AI
0 likes285 views
The document discusses how graphs can enhance AI and machine learning by providing structured connectivity data and features derived from graph algorithms, embeddings, and neural networks. It outlines steps for doing graph data science, including building knowledge graphs, developing graph-based features, and using graph neural networks. The document also provides examples of applying these graph techniques across domains like financial services, healthcare, and recommendations.
How Graphs Enhance AI
- 1. Amy E. Hodler Graph Analytics & AI Program Manager, Neo4j Amy.Hodler@neo4j.com @amyhodler How Graphs Enhance AI Graphs in Data Science Advancing through the Steps of Graph Data Science
- 4. Predicting Financial Contagion from Global to Local
- 5. Financial Crimes Drug Discovery Recommendations Cybersecurity Predictive Maintenance Customer Segmentation Churn Prediction Search/MDM Graphs Data Science Applications
- 6. “The idea is that graph networks are bigger than any one machine-learning approach. Graphs bring an ability to generalize about structure that the individual neural nets don't have.” "Where do the graphs come from that graph networks operate over?”
- 8. Building a Graph ML Model Data Sources Native Graph Platform Machine Learning Aggregate Disparate Data and Cleanse Build Predictive Models Unify Graphs and Engineer Features Parquet JSON and more… MLlib and more…
- 9. Spark Graph Native Graph Platform Machine Learning Example: Spark & Neo4j Workflow Graph Transactions Graph Analytics Cypher 9 in Spark 3.0 to create non- persistent graphs MLlib to Train Models Native Graph Algorithms, Processing, and Storage Morpheus integration
- 10. Explore Graphs Build Graph Solutions • Massively scalable • Powerful data pipelining • Robust ML Libraries • Non-persistent, non-native graphs • Persistent, dynamic graphs • Graph native query and algorithm performance • Constantly growing list of graph algorithms and embeddings
- 11. Steps Forward 11
- 12. Steps Forward in Graph Data Science Graph Persistence Knowledge Graphs Connected Feature Engineering Graph Native Learning
- 13. Steps Forward in Graph Data Science Query Based Knowledge Graph Query Based Feature Engineering Graph Algorithm Feature Engineering Graph Embeddings Graph Neural Networks Enterprise Delivery DataScienceComplexity Knowledge Graphs Graph Feature Engineering Graph Native Learning Graph Persistence
- 14. Steps Forward in Graph Data Science Query Based Knowledge Graph Query Based Feature Engineering Graph Algorithm Feature Engineering Graph Embeddings Graph Neural Networks Enterprise Maturity DataScienceComplexity
- 15. Query-Based Knowledge Graphs Connecting the Dots • Multiple graph layers of financial information • Includes corporate data with cross-relationships, external news, and customized weighting • Dashboards and tools • Credit risk • Investment risk • Portfolio news recommendations
- 16. Steps Forward in Graph Data Science Query Based Knowledge Graph Graph Algorithm Feature Engineering Graph Embeddings Graph Neural Networks Query Based Feature Engineering Enterprise Maturity DataScienceComplexity
- 17. HetioNet is a knowledge graph integrating over 50 years of biomedical data Leveraged to predict new uses for drugs by using the graph topology to create features to predict new links Query-Based Feature Engineering Mining Data for Drug Discovery het.io
- 18. Query-Based Feature Engineering Mining Data for Drug Discovery HetioNet is a knowledge graph integrating over 50 years of biomedical data Leveraged to predict new uses for drugs by using the graph topology to create features to predict new links het.io
- 19. Query-Based Feature Engineering Mining Data for Drug Discovery
- 20. Spark Graph Native Graph Platform Machine Learning • Merge distributed data into DataFrames • Reshape your tables into graphs • Explore cypher queries • Move to Neo4j to build expert queries • Persist your graph Knowledge Graphs: Getting Started Example with Spark • Bring query based graph features to ML pipeline Graph Transactions Graph Analytics
- 21. Steps Forward in Graph Data Science Query Based Feature Engineering Graph Embeddings Graph Neural Networks Query Based Knowledge Graph Graph Algorithm Feature Engineering Enterprise Maturity DataScienceComplexity
- 22. Feature Engineering is how we combine and process the data to create new, more meaningful features, such as clustering or connectivity metrics. Graph Connected Feature Engineering Add More Descriptive Features: - Influence - Relationships - Communities Extraction
- 23. 23 Graph Feature Categories & Algorithms Pathfinding & Search Finds the optimal paths or evaluates route availability and quality Centrality / Importance Determines the importance of distinct nodes in the network Community Detection Detects group clustering or partition options Heuristic Link Prediction Estimates the likelihood of nodes forming a relationship Evaluates how alike nodes are Similarity Embeddings Learned representations of connectivity or topology
- 24. • Connected components to identify disjointed graphs sharing identifiers • PageRank to measure influence and transaction volumes • Louvain to identify communities that frequently interact • Jaccard to measure account similarity 24 Graph Connected Feature Engineering Financial Crime: Detecting Fraud Large financial institutions already have existing pipelines to identify fraud via heuristics and models Graph based features improve accuracy:
- 25. +48,000 U.S. Patents for Graph Fraud / Anomaly Detection in the last 10 years
- 26. Spark Graph Native Graph Platform Machine Learning • Merge distributed data into DataFrames • Reshape your tables into graphs • Explore cypher queries and simple algorithms • Persist your graph • Create rule based features • Run native graph algorithms and write to graph or stream Graph Feature Engineering: Getting Started Example with Spark • Bring graph features to ML pipeline for training Graph Transactions Graph Analytics
- 27. 27 Graph Algorithms in Neo4J • Parallel Breadth First Search • Parallel Depth First Search • Shortest Path • Single-Source Shortest Path • All Pairs Shortest Path • Minimum Spanning Tree • A* Shortest Path • Yen’s K Shortest Path • K-Spanning Tree (MST) • Random Walk • Degree Centrality • Closeness Centrality • CC Variations: Harmonic, Dangalchev, Wasserman & Faust • Betweenness Centrality • Approximate Betweenness Centrality • PageRank • Personalized PageRank • ArticleRank • Eigenvector Centrality • Triangle Count • Clustering Coefficients • Connected Components (Union Find) • Strongly Connected Components • Label Propagation • Louvain Modularity – 1 Step & Multi-Step • Balanced Triad (identification) • Euclidean Distance • Cosine Similarity • Jaccard Similarity • Overlap Similarity • Pearson Similarity Pathfinding & Search Centrality / Importance Community Detection Similarity neo4j.com/docs/ graph-algorithms/current/ Link Prediction • Adamic Adar • Common Neighbors • Preferential Attachment • Resource Allocations • Same Community • Total Neighbors
- 28. Steps Forward in Graph Data Science Query Based Knowledge Graph Graph Algorithm Feature Engineering Graph Neural Networks Query Based Feature Engineering Graph Embeddings Enterprise Maturity DataScienceComplexity
- 29. Embedding transforms graphs into a feature vector, or set of vectors, describing topology, connectivity, or attributes of nodes and edges in the graph 29 Graph Embeddings • Vertex/Node embeddings: describe connectivity of each node • Path embeddings: traversals across the graph • Graph embeddings: encode an entire graph into a single vector
- 30. Explainable Reasoning over Knowledge Graphs for Recommendation 30 Graph Embeddings - Recommendations
- 31. 31 Graph Embeddings - Recommendations Explainable Reasoning over Knowledge Graphs for Recommendation
- 32. Spark Graph Native Graph Platform Machine Learning • Merge distributed data into DataFrames • Reshape your tables into graphs • Explore cypher queries and simple algorithms • Move to Neo4j to build expert queries • Write to persist • Stay tuned for DeepWalk and DeepGL algorithms Graph Feature Engineering-Embedding: Getting Started Example with Spark • Bring graph features to ML pipeline for training Graph Transactions Graph Analytics
- 33. Steps Forward in Graph Data Science Query Based Knowledge Graph Graph Algorithm Feature Engineering Query Based Feature Engineering Graph Neural Networks Graph Embeddings Enterprise Maturity DataScienceComplexity
- 34. Deep Learning refers to training multi-layer neural networks using gradient descent 34 Graph Native Learning
- 35. Graph Native Learning refers to deep learning models that take a graph as an input, performs computations, and return a graph 35 Graph Native Learning Battaglia et al, 2018
- 36. Example: electron path prediction Bradshaw et al, 2019 36 Graph Native Learning Given reactants and reagents, what will the products be? Given reactants and reagents, what will the products be?
- 37. Steps Forward in Graph Data Science Query Based Knowledge Graph Query Based Feature Engineering Graph Algorithm Feature Engineering Graph Embeddings Graph Neural Networks Enterprise Delivery DataScienceComplexity Knowledge Graphs Graph Feature Engineering Graph Native Learning Graph Persistence
- 38. Resources Business • neo4j.com/use-cases/ artificial-intelligence-analytics/ • AI Whitepaper Data Scientists/Developers • neo4j.com/sandbox • neo4j.com/developer/ • community.neo4j.com Amy.Hodler@neo4j.com @amyhodler neo4j.com/ graph-algorithms-book