Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Upcoming SlideShare
What to Upload to SlideShare
Next

Share

Graph-Powered Machine Learning

Graph-Powered Machine Learning - Meetup Paris - March 5, 2018

Graph -based machine learning is becoming an important trend in artificial intelligence, transcending a lot of other techniques. Using graphs as a basic representation of data for multiple purposes:
- the data is already modeled for further analysis
- graphs can easily combine multiple sources into a single graph representation and learn over them, creating Knowledge Graphs;
- improving computation performances and quality. The talk will present these advantages and present applications in the context of recommendation engines and natural language processing.

Speaker: Dr. Vlasta Kus (@VlastaKus) is a Data Scientist at GraphAware, specializing in graph-based Natural Language Processing and related topics, including deep learning techniques. He speaks English, Czech and some French and currently lives in Prague.

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all

Graph-Powered Machine Learning

  1. 1. GraphAware® GRAPH POWERED MACHINE LEARNING Vlasta Kůs, Data Scientist @ GraphAware graphaware.com @graph_aware, @VlastaKus
  2. 2. WHAT IS MACHINE LEARNING? GraphAware® [Machine Learning is the] field of study that gives computers the ability to learn without being explicitly programmed. 
 — Arthur Samuel, 1959
  3. 3. WHAT IS A GRAPH? GraphAware® G = (V, E)
  4. 4. WHY NEO4J? GraphAware® It is a proper graph database It is a proper database
  5. 5. MACHINE LEARNING LIFECYCLE GraphAware®
  6. 6. MACHINE LEARNING CHALLENGES The Source of Truth Performance Model Storing Real Time
  7. 7. THE SOURCE OF TRUTH GraphAware® “Even the best learning algorithm
 on wrong data produces wrong results.” 
 — Alessandro Negro, 2015
  8. 8. THE SOURCE OF TRUTH GraphAware® Source: Michele Banko and Eric Brill Scaling to Very Very Large Corpora for Natural Language Disambiguation - 2001
  9. 9. THE SOURCE OF TRUTH GraphAware®Source: https://www.domo.com/learn/data-never-sleeps-5
  10. 10. Predictive accuracy Training Performance Prediction Performance Ability to scale PERFOMANCE GraphAware®
  11. 11. NEO4J CAUSAL CLUSTER GraphAware®Source: https://neo4j.com/docs/operations-manual/
  12. 12. Store the results of the training phase Provide multiple access patterns Mix models The size depends on the algorithm STORING THE RESULTS & MODEL GraphAware®
  13. 13. LEARN FAST PREDICT FAST REAL TIME
  14. 14. GraphAware®
  15. 15. STORING DATA SOURCES: TENSOR GraphAware® Simple Recommendation f: User x Item -> Relevance Score Context Aware Recommendation f: User x Item x Context1 x Context2 x Context3 -> Relevance Score
  16. 16. The results of machine learning process can be stored in a graph as well. Some examples are:
 ‣ Similarity (k-Nearest Neighbours) ‣ Cluster ‣ Spanning Tree ‣ Decision Tree ‣ Random forest ‣ Markov Chain STORING RESULTS & MODELS GraphAware®
  17. 17. STORING RESULTS & MODELS GraphAware® K-Nearest Neighbours Markov Chain Decision Tree
  18. 18. STORING DATA SOURCES: KNOWLEDGE GRAPH GraphAware®
  19. 19. GraphAware®
  20. 20. ‣ NLP and graphs: natural fit GRAPH-BASED NATURAL LANGUAGE PROCESSING GraphAware® ‣ Knowledge enrichment Source: http://nlp.stanford.edu:8080/corenlp/process
  21. 21. Unsupervised techniques tend to be underestimated … ‣ No need for time & money to get massive labeled training datasets ‣ Often faster to train & faster to predict ‣ Unsupervised deep learning UNSUPERVISED ML ALGORITHMS GraphAware®
  22. 22. Some graph-native algorithms that are relevant to machine learning processes:
 ‣ Random Walk ‣ Page Rank ‣ Graph Matching ‣ Shortest Path ‣ Depth-First Graph Traversal ‣ Breadth-First Graph Traversal ‣ Minimum Spanning Tree ‣ Graph Clustering ‣ Node2vec GRAPH-BASED ML ALGORITHMS GraphAware®
  23. 23. pressure information system telemetry spacecraft power critical ground command performance component drive connector standard software operation testing environmental flight damage spare subsystem orbiter posit flight software control instrument propellant flight project program resource equipment fluid re condition analysis servicemaintenance device electrical circuit area accident number management risk implem significant personnel exploration rover facility human effect event life lack loss potential review ground system engineering different configuration control configuration logistics datum NASA ground processing processing safety verification risk management part t launch pipe shuttle leak lesson load environment space check line source training factor material due practice capability battery flight hardware government assembly figure evm space shuttle surface operational thermal installation many set one inspection propulsion system actuator impact flight system launch vehicle flow current leakage shuttle program digital mishap propulsion engine complete NASA program fault attitude science flight operation mission operation independent investigation JPL fire procedure torque incident mars space system general critical hardware fault protection mer user system engineering expertisespace flight manager project manager mitigation Pegasus actuator system amp capability legacy actuator system output control system different manager many review purpose appropriate f integration important ground testing computer flight equipment independent review space hardware software development ssme technical content value management aerodynamic load aerodynamic ppe deceased successful implementation formal mishap investigation lax GRAPH-BASED ML ALGORITHMS:
 PAGE RANK GraphAware® Keywords Extraction Rada Mihalcea, Paul Tarau. 2004. TextRank: Bringing Order into Texts. Proceedings of EMNLP 2004, pages 404–411, Barcelona, Spain. Association for Computational Linguistics. http://www.aclweb.org/anthology/W04-3252.
  24. 24. GRAPH-BASED ML ALGORITHMS:
 GRAPH CLUSTERING GraphAware® Continuous Cellular Tower Data Analysis Eagle N., Quinn J.A., Clauset A. (2009) Methodologies for Continuous Cellular Tower Data Analysis. In: Tokuda H., Beigl M., Friday A., Brush A.J.B., Tobe Y. (eds) Pervasive Computing. Pervasive 2009. Lecture Notes in Computer Science, vol 5538. Springer, Berlin, Heidelberg
  25. 25. GraphAware®
  26. 26. GRAPH VISUALIZATION GraphAware®
  27. 27. ‣ Meet us tomorrow at Neo4j GraphTour ‣ Come to our meet-ups graphaware.com/events ‣ Visit our blog graphaware.com/blog ‣ Watch us youtube.com -> GraphAware channel ‣ And most importantly … Get in touch! INTERESTED IN MORE? GraphAware®
  28. 28. www.graphaware.com @graph_aware
  • ditnux

    Dec. 18, 2018
  • zengxijin

    Oct. 12, 2018
  • KwanyuetHoPhD

    Apr. 19, 2018

Graph-Powered Machine Learning - Meetup Paris - March 5, 2018 Graph -based machine learning is becoming an important trend in artificial intelligence, transcending a lot of other techniques. Using graphs as a basic representation of data for multiple purposes: - the data is already modeled for further analysis - graphs can easily combine multiple sources into a single graph representation and learn over them, creating Knowledge Graphs; - improving computation performances and quality. The talk will present these advantages and present applications in the context of recommendation engines and natural language processing. Speaker: Dr. Vlasta Kus (@VlastaKus) is a Data Scientist at GraphAware, specializing in graph-based Natural Language Processing and related topics, including deep learning techniques. He speaks English, Czech and some French and currently lives in Prague.

Views

Total views

7,799

On Slideshare

0

From embeds

0

Number of embeds

5,398

Actions

Downloads

0

Shares

0

Comments

0

Likes

3

×