Knowledge graphs generation is outpacing the ability to intelligently use the information that they contain. Octavian's work is pioneering Graph Artificial Intelligence to provide the brains to make knowledge graphs useful. Our neural networks can take questions and knowledge graphs and return answers. Imagine: a google assistant that reads your own knowledge graph (and actually works) a BI tool reads your business' knowledge graph a legal assistant that reads the graph of your case Taking a neural network approach is important because neural networks deal better with the noise in data and variety in schema. Using neural networks allows people to ask questions of the knowledge graph in their own words, not via code or query languages. Octavian's approach is to develop neural networks that can learn to manipulate graph knowledge into answers. This approach is radically different to using networks to generate graph embeddings. We believe this approach could transform how we interact with databases.

1. Graph AI

2. CLOUD_ENGINEER AI_RESEARCHER
This talk does not represent the views of Neo4j
{
name: “Andrew Jefferson”
}

3. What is a graph?
...

5. What is a graph?
Why are we interested in graphs?
...

6. (Graphs)-[ARE]->(Everywhere)

7. What is a graph?
Why are we interested in graphs?
What is AI?
...

8. What is a graph?
Why are we interested in graphs?
What is AI?
What is Deep Learning?
...

11. 90% accuracy

12. Machine learning
trained_model = train(model, data)
learned_weights = trained_model.get_weights()
prediction = trained_model.predict(instance)

13. Machine learning
trained_model = train(model, data)
learned_weights = trained_model.get_parameters()
prediction = trained_model.predict(instance)
Model Learned Params Training Data
Linear Regression y = mx + c m, c List<(x, y)>
Basic Classifier P(class | x) = softmax((dense(w, x)) w class set
List<(x, class)>
NN Embedding P(context | word) = NN(word) word embedding,
NN weights
word dictionary
List<(context, word)>

14. Deep Learning = ML using Deep Neural Networks
trained using gradient descent

15. What is a graph?
Why are we interested in graphs?
What is Deep Learning?
What is Deep Learning on graphs?
...

16. Model Learned Params Data
Linear Regression y = mx + c m List<(x, y)>
Image Classifier P(class | image) = CNN(image) CNN weights List<(image, class)>
NN Embedding P(path | node) = NN(path) node embedding,
NN weights
Node dictionary
List<(path, node)>
Graph Regression node.prop = F([sub]graph) F weights List<(node, [sub]graph)>
or Graph, pattern
Graph Classifier P(class | [sub]graph) = F([sub]graph) F weights List<([sub]graph, class)>
or Graph, pattern
Graph Embedder P(subgraph | node) = F(graph) node embedding,
F weights
Graph

17. How’s that going?

18. How to DL
Graphs - the dimensionality challenge!
How to encode a variable graph into a fixed size matrix?

19. Graphs, Neural Networks and Structural Priors
“DL is good for unstructured data”
... bad at structured data: THIS IS NOT TRUE
DL is good at very specific data structures:
Images: Sequences:

20. Images: Sequences:

21. Images: Convolutional Network

22. What about graphs?
Graph AI is more than a “how to vectorise a graph” challenge!

23. What about graphs?
Graph AI is more than a “how to vectorise a graph” challenge!

24. What about graphs?
Graph AI is more than a “how to vectorise a graph” challenge!

25. How to do Deep Learning on Graphs
Graphs - the dimensionality challenge
How to encode a variable graph into a fixed size matrix?
Graphs - the inductive bias challenge?
How can we structure a neural network to retain graph structural priors?

27. Graph Networks

28. Graph Memory Network

29. What is a graph?
Why are we interested in graphs?
What is Deep Learning?
What is Deep Learning on graphs?
Does it work?

30. CLEVR-GRAPH
https://github.com/Octavian-ai/clevr-graph
A synthetic dataset where 100% accuracy is
achievable.

31. CLEVR-GRAPH
https://github.com/Octavian-ai/clevr-graph

32. CLEVR-GRAPH
https://github.com/Octavian-ai/clevr-graph

33. What is the cleanliness level of {Station} station?
99.9% accuracy after 10k training steps
How big is {Station}?
What music plays at {Station}?
What architectural style is {Station}?
Describe {Station} station's architectural style.
Is there disabled access at {Station}?
Does {Station} have rail connections?
Can you get rail connections at {Station}?
Are {Station} and {Station} adjacent? 99% accuracy after 20k training steps
Which {Architecture} station is adjacent to {Station}? 98.8% accuracy after 30k training steps
How many stations are between {Station} and {Station}?
98% accuracy up to ~9 apart after 25k training
steps
Are {Station} and {Station} connected by the same station?
98% accuracy after 20k steps
Which station is adjacent to {Station} and {Station}?
Is there a station called {Station}?
99.9% accuracy after 30k training steps
Is there a station called {FakeStationName}?
Are {Station} and {Station} on the same line? Not yet tested
How many architectural styles does {Line} pass through? Not yet tested
How many music styles does {Line} pass through? Not yet tested
How many sizes of station does {Line} pass through? Not yet tested
How many stations with rail connections does {Line} pass through? Not yet tested
Which lines is {Station} on? Not yet tested
How many lines is {Station} on? Not yet tested
Which stations does {Line} pass through? Not yet tested

34. What is a graph?
Why are we interested in graphs?
What is Deep Learning?
What is Deep Learning on graphs?
?Does it work? … How does it work?

35. Graph Q&A
“How many stations are between Bank and Temple?”
Graph Networks gave us a method for propagating information through
the graph. How do we prime the graph to answer our specific query?

36. How to do Deep Learning on Graphs
Graphs - the dimensionality challenge
How to encode a variable graph into a fixed size matrix?
Graphs - the inductive bias challenge?
How can we structure a neural network to retain graph structural priors?
Graphs - the starting condition challenge?
How do we prime the graph to answer our specific query?

38. Attention

41. https://github.com/Octavian-ai/mac-graph

42. Deep Learning on Graphs
● DL model that can learn how to navigate a graph schema
● End-to-end training on List<(x, y, graph)>
● A single DL model can learn to solve multiple problems
○ Using multiple algorithms

43. Thanks
https://octavian.ai
@Octavian_ai
@EastlondonDev
hello@octavian.ai

45. Regular vs Graph Classifier
Model Learned Weights Data
P(class | x_features) = NN(x_features) NN weights List<(x_features, class)>
Works well if your features are easily vectorised and uniform length.
No vectorisation required, can handle extremely heterogeneous data.
Model Learned Weights Data
P(class | [sub]graph) = NN([sub]graph) NN weights List<([sub]graph, class)>

46. Images: Sequences:
Retail: London
Underground:

47. We can barely handle the small data sets intelligently, let alone the large ones
Issues
- Absence of useful graph techniques
- Either large scale and statistical
- Rule based and inflexible
Neither help deal with real world graph queries:

50. Trusted consumer brand
Quality handheld electronics
manufacturing
Battery and HDD
technology (from laptops)
Integration with music
software on a pc
Fast data transfer
(Firewire)

51. Battery and HDD
technology (from laptops)
Integration with music
software on a pc
Fast data transfer
(Firewire) 1995
Trusted consumer brand
Quality handheld electronics
manufacturing

52. Why are graphs useful?

53. Graph Analytics
Pattern matching
Recommendations
Fraud Detection
Optimisation

54. What am I going to tell you?
1) What is a graph and why are we interested in graphs? ✓
2) a tiny nod to "traditional" graph ML
3) Terminology: DL := "Deep learning with Neural Networks" (optionally Reinforcement)
4) Deep Learning is cool, some examples
5) People think DL is good for unstructured data and bad at structured data: THIS IS NOT TRUE
- DL is good at very specific data structures: grids and sequences of single entities
6) General state of the world of "AI" on graphs (basically a walkthrough of the Relational Inductuve Bias' paper)
7) Some specific knowledge graph architecture

55. Many kinds of graphs, Many kinds of AI
Connectivity Graph
Hallmarks: Concerned with individual entities. Has very small number of node and relationship types
(often just 1 of each). Distance between nodes is meaningful. Generally a single connected graph
Example: Simple social graph, Netflix graph, Transit graph
Algorithms: Shortest path, Neighbourhood, Recommendation, Link Prediction
Knowledge Graph
Hallmarks: Describes an abstraction. Has large number of node _or_ relationship types (or both). Distance
between nodes is not meaningful. May be multiple unconnected graphs
Example: Medical research database, Marketing graph, Ontologies
Algorithms: Inference, Question answering, Property Prediction

56. Many kinds of graphs, Many kinds of AI
Hybrid Graphs
Hallmarks: Distance between nodes may or may not be meaningful depending on the relationship type.
Example: Online shop database, Communication graph, Sophisticated Transaction graph
Algorithms: Inference, Recommendation, Link/Property Prediction
We can classify graphs in all kinds of ways, but it’s a relatively futile exercise
Graph AI may be quite specific, predicated on a particular graph properties, or it might be flexible. We are
interested in both!

57. Graph Classifier
Train( model, (y)-[..2]-(), y.is_fraud )
Train( model, (p:Person)<-[r:FRIEND_OF]-(:Person)->(), p.favorite_animal )
Train( model, (c:Company)-[..3]->(), c.future_value )

58. How to DL?
I will show four different examples.
Each example has a different Deep Learning inspired method to solve a different
kind of problem

59. How to DL? Learn a node or edge embedding using a mathematical model
Does not necessarily involve Neural Networks!
We have to invent/choose the mathematical function we will use
Overcomes the dimensionality challenge using Random Walks
Example: Review prediction with dot
https://medium.com/octavian-ai/review-prediction-with-neo4j-and-tensorflow-1c
d33996632a
DeepWalk, node2vec create Word2Vec style embeddings based on
_connections_
DeepGL creates features based on other graph properties

60. How to DL? Learn an embedding _and_ an interaction fn at the same time
Example? Deep

61. How to DL? Construct graph queries using DL (Tool Use)
Translate questions into graph queries:
https://medium.com/octavian-ai/answer
ing-english-questions-using-knowledge
-graphs-and-sequence-translation-2ac
baa35a21d
Sidesteps the dimensionality challenge
completely

62. How to DL? Treat nodes and relations as tables
Example: property queries on CLEVR graph:
https://medium.com/octavian-ai/graphs-and-neural-networks-reading-node-propert
ies-2c91625980eb
Uses attention to overcome the dimensionality challenge.
Doesn’t use the graph structure though

63. How to DL? Transmit signals from nodes in the graph
Uses attention and message passing

64. Knowledge Graphs
Connections (relations) are important
Enormous linked data sets exist (knowledge graphs)
Small linked data sets also exist (legal cases, personal graphs)

65. Existing Graph DL
1) Categorisation
2) Link Prediction
3) Chemistry
These don’t help much with our knowledge graphs!
We want something different to existing graph DL
1) Should work on relatively small graphs
2) Should facilitate querying the graph to extract information/predictions based
on the graph and the query

66. Deep Learning for Knowledge Graphs
Step 1: We need a metric that we can use to test our “AI”.
Step 2:

67. Deep Learning for Knowledge Graphs
Node Properties and Graph Structure (relationships) are both important to a
knowledge graph.
Knowledge graph queries depend on multiple nodes & graph structure.
Node/edge embeddings don’t capture the necessary information.

68. Everything is a graph
● Organisation Chart
● Social Network
● Product Reviews
● Blockchain
● Supply Chain
● Chemical Structure
● Mechanical Structure
● Travel Itinerary
● The Internet
●

69. Knowledge graphs generation is outpacing the ability to intelligently use the information that they contain. Octavian's work is pioneering Graph Artificial
Intelligence to provide the brains to make knowledge graphs useful.
Our neural networks can take questions and knowledge graphs and return answers. Imagine:
- a google assistant that reads your own knowledge graph (and actually works)
- a BI tool reads your business' knowledge graph
- a legal assistant that reads the graph of your case
Taking a neural network approach is important because neural networks deal better with the noise in data and variety in schema. Using neural networks
allows people to ask questions of the knowledge graph in their own words, not via code or query languages.
Octavian's approach is to develop neural networks that can learn to manipulate graph knowledge into answers. This approach is radically different to using
networks to generate graph embeddings. We believe this approach could transform how we interact with databases.

71. What is a graph?

72. Model Learned Weights Data
NN Embedding P(path | node) = NN(node) node embedding,
NN weights
Node dictionary
List<(path, node)>
Train_Embedding( MATCH (n)-[..2]->(m) , n)

73. Model Learned Weights Data
Graph Classifier P(class | [sub]graph) = NN([sub]graph) NN weights List<([sub]graph, class)>
or Graph, pattern
Train_Classifier( MATCH (n)-[..2]->(m) , n.is_fraud)

74. Semantic Graphs
Powerful question-answering tool
Using simple rules and a managed schema
Great for 20 questions / what am I?
Flädlesuppe-[contains]->Pancake-[contains]->Milk-[is]->Dairy

75. Q&A chat bot
Determine the entity and property
Do cats have spines?
-> { entity: “felis catus”,
property: “ vertebra”, value: true }
Use a graph query
({name: “felis catus”})-[IS_A..*]->()-[HAS_A]->({vertebra {name: “vertebra”}})
Convert the graph path:
Yes. Cats (felis catus) is a Mammal. Mammals have spines
(vertebra)

76. Bibliography
“Relational inductive biases, deep learning, and graph networks” https://arxiv.org/abs/1806.01261