learning from limited labeled data but a lot of unlabeled
play

Learning from Limited Labeled Data (but a lot of unlabeled data) - PowerPoint PPT Presentation

Sep 19, 2022 •151 likes •582 views

Learning from Limited Labeled Data (but a lot of unlabeled data) NELL as a case study Tom M. Mitchell Carnegie Mellon University Thesis: We will never really understand learning until we build machines that learn many different things,

  1. Learning from Limited Labeled Data (but a lot of unlabeled data) NELL as a case study Tom M. Mitchell Carnegie Mellon University

  2. Thesis: We will never really understand learning until we build machines that • learn many different things, • from years of diverse experience, • in a staged, curricular fashion, • and become better learners over time.

  3. NELL: Never-Ending Language Learner The task: • run 24x7, forever • each day: 1. extract more facts from the web to populate the ontology 2. learn to read (perform #1) better than yesterday Inputs: • initial ontology (categories and relations) • dozen examples of each ontology predicate • the web • occasional interaction with human trainers

  4. NELL today Running 24x7, since January, 12, 2010 Result: • KB with ~120 million confidence-weighted beliefs • learning to read • learning to reason • extending ontology

  5. NELL knowledge fragment football uses * including only correct beliefs equipment climbing skates helmet Canada Sunnybrook Miller uses equipment city hospital Wilson company country hockey Detroit GM politician CFRB radio Pearson Toronto hometown play hired competes airport home town with Stanley city Maple Leafs Red Cup company city won won Wings Toyota stadium team stadium league league Connaught city acquired paper city Air Canada NHL member created stadium Hino Centre plays in economic sector Globe and Mail Sundin Prius writer automobile Toskala Skydome Corrola Milson

  6. [Mitchell et al., CACM 2017] Improving Over Time Never Ending Language Learner 10’s of millions of beliefs reading skill tens of millions of beliefs à mean avg precision à 2010 time à 2016 2010 time à 2017

  7. Y: person f: X à Y X: noun phrase hard (underconstrained) semi-supervised learning

  8. Key Idea: Massively coupled semi-supervised training person sport athlete coach team Y: person f: X à Y noun phrase noun phrase noun phrase text context morphology URL specific X: noun phrase “ __ is my son ” ends in ‘ … ski’ appears in list2 at URL35401 hard much easier (underconstrained) (more constrained) semi-supervised semi-supervised learning learning

  9. Supervised training of 1 function : y : person x :

  10. Coupled training of 2 functions : y : person x :

  11. NELL Learned Contexts for “Hotel” (~1% of total) "_ is the only five-star hotel” "_ is the only hotel” "_ is the perfect accommodation" "_ is the perfect address” "_ is the perfect lodging” "_ is the sister hotel” "_ is the ultimate hotel" "_ is the value choice” "_ is uniquely situated in” "_ is Walking Distance” "_ is wonderfully situated in” "_ las vegas hotel” "_ los angeles hotels” "_ Make an online hotel reservation” "_ makes a great home-base” "_ mentions Downtown” "_ mette a disposizione” "_ miami south beach” "_ minded traveler” "_ mucha prague Map Hotel” "_ n'est qu'quelques minutes” "_ naturally has a pool” "_ is the perfect central location” "_ is the perfect extended stay hotel” "_ is the perfect headquarters” "_ is the perfect home base” "_ is the perfect lodging choice" "_ north reddington beach” "_ now offer guests” "_ now offers guests” "_ occupies a privileged location” "_ occupies an ideal location” "_ offer a king bed” "_ offer a large bedroom” "_ offer a master bedroom” "_ offer a refrigerator” "_ offer a separate living area" "_ offer a separate living room” "_ offer comfortable rooms” "_ offer complimentary shuttle service” "_ offer deluxe accommodations” "_ offer family rooms” "_ offer secure online reservations” "_ offer upscale amenities” "_ offering a complimentary continental breakfast” "_ offering comfortable rooms” "_ offering convenient access” "_ offering great lodging” "_ offering luxury accommodation” "_ offering world class facilities” "_ offers a business center" "_ offers a business centre” "_ offers a casual elegance” "_ offers a central location” “_ surrounds travelers” …

  12. NELL Highest Weighted* string fragments: “Hotel” 1.82307 SUFFIX=tel 1.81727 SUFFIX=otel 1.43756 LAST_WORD=inn 1.12796 PREFIX=in 1.12714 PREFIX=hote 1.08925 PREFIX=hot 1.06683 SUFFIX=odge 1.04524 SUFFIX=uites 1.04476 FIRST_WORD=hilton 1.04229 PREFIX=resor 1.02291 SUFFIX=ort 1.00765 FIRST_WORD=the 0.97019 SUFFIX=ites 0.95585 FIRST_WORD=le 0.95574 PREFIX=marr 0.95354 PREFIX=marri 0.93224 PREFIX=hyat 0.92353 SUFFIX=yatt 0.88297 SUFFIX=riott 0.88023 PREFIX=west * logistic regression 0.87944 SUFFIX=iott

  13. Type 1 Coupling: Co-Training, Multi-View Learning Theorem (Blum & Mitchell, 1998) : y : person If f 1 ,and f 2 are PAC learnable from noisy labeled data, and X 1 , X 2 are conditionally independent given Y, Then f 1 , f 2 are PAC learnable from polynomial unlabeled data plus a weak initial predictor x :

  14. Type 1 Coupling: Co-Training, Multi-View Learning [Blum & Mitchell; 98] [Dasgupta et al; 01 ] [Balcan & Blum; 08] [Ganchev et al., 08] y : person [Sridharan & Kakade, 08] [Wang & Zhou, ICML10] x :

  15. Type 1 Coupling: Co-Training, Multi-View Learning [Blum & Mitchell; 98] sample complexity drops exponentially [Dasgupta et al; 01 ] in the number of views of X [Balcan & Blum; 08] [Ganchev et al., 08] y : person [Sridharan & Kakade, 08] [Wang & Zhou, ICML10] x :

  16. Type 2 Coupling: Multi-task, Structured Outputs [Daume, 2008] [Bakhir et al., eds. 2007] [Roth et al., 2008] [Taskar et al., 2009] person sport [Carlson et al., 2009] athlete coach team subset/superset athlete(NP) à person(NP) NP mutual exclusion athlete(NP) à NOT sport(NP) sport(NP) à NOT athlete(NP)

  17. Multi-view, Multi-Task Coupling person sport athlete coach team NP text NP NP HTML NP : context morphology contexts distribution

  18. Type 3 Coupling: Relations and Argument Types playsSport(a,s) coachesTeam(c,t) playsForTeam(a,t) teamPlaysSport(t,s) NP1 NP2

  19. Type 3 Coupling: Relations and Argument Types playsSport(a,s) coachesTeam(c,t) playsForTeam(a,t) teamPlaysSport(t,s) person sport person sport athlete athlete team coach team coach NP1 NP2

  20. Type 3 Coupling: Relations and Argument Types playsSport(NP1,NP2) à athlete(NP1), sport(NP2) playsSport(a,s) coachesTeam(c,t) playsForTeam(a,t) teamPlaysSport(t,s) person sport person sport athlete athlete team coach team coach NP1 NP2

  21. Type 3 Coupling: Relations and Argument Types over 4000 coupled functions in NELL playsSport(a,s) coachesTeam(c,t) playsForTeam(a,t) teamPlaysSport(t,s) person sport person sport athlete athlete team coach team coach NP1 1 NP1 2 NP2 1 NP2 multi-view consistency subset/superset argument type consistency mutual exclusion

  22. How to train approximation to EM: • E step: predict beliefs from unlabeled data (ie., the KB) • M step: retrain NELL approximation: • bound number of new beliefs per iteration, per predicate • rely on multiple iterations for information to propagate, partly through joint assignment, partly through training examples Better approximation: • Joint assignments based on probabilistic soft logic [Pujara, et al., 2013] [Platanios et al., 2017]

  23. If coupled learning is the key, how can we get new coupling constraints?

  24. Key Idea 2: Learn new coupling constraints • first order, probabilistic horn clause constraints: 0.93 athletePlaysSport(?x,?y) ß athletePlaysForTeam(?x,?z) teamPlaysSport(?z,?y) – learned by data mining the knowledge base – connect previously uncoupled relation predicates – infer new unread beliefs – NELL has 100,000s of learned rules – uses PRA random-walk inference [Lao, Cohen, Gardner]

  25. Key Idea 2: Learn inference rules PRA: [Lao, Mitchell, Cohen, EMNLP 2011] competes economic If: x1 x2 x3 with sector (x1,x2) (x2, x3) Then: economic sector (x1, x3) with probability 0.9

  26. Key Idea 2: Learn inference rules PRA: [Lao, Mitchell, Cohen, EMNLP 2011] economic sector competes economic If: x1 x2 x3 with sector (x1,x2) (x2, x3) Then: economic sector (x1, x3) with probability 0.9

  27. Learned Rules are New Coupling Constraints! 0.93 playsSport(?x,?y) ß playsForTeam(?x,?z), teamPlaysSport(?z,?y) playsSport(a,s) coachesTeam(c,t) playsForTeam(a,t) teamPlaysSport(t,s) person sport person sport athlete athlete team coach team coach NP1 NP2

  28. Learned Rules are New Coupling Constraints! • Learning X makes one a better learner of Y • Learning Y makes one a better learner of X X = reading functions: text à beliefs Y = Horn clause rules: beliefs à beliefs

  29. Consistency and Correctness what is the relationship? under what conditions? link between learning and error estimation

  30. [Platanios, Blum, Mitchell] Problem setting: • have N different estimates of target function = NELL category “city” = classifier based on i th view of = noun phrase

  31. Problem setting: • have N different estimates of target function = disease = i th diagnostic test = medical patient [Hui & Walter, 1980; Collins & Huynh, 2014]

Recommend

Co-Training Based on Combining Labeled and Unlabeled Data with Co-Training by A. Blum

Co-Training Based on Combining Labeled and Unlabeled Data with Co-Training by A. Blum

0. Co-Training Based on Combining Labeled and Unlabeled Data with Co-Training by A. Blum & T. Mitchell, 1998 1. Problem: Learning to classify data (ex: web pages) when the description of each example can be partitioned in 2

560 views • 9 slides
10701 Semi supervised learning Can Unlabeled Data improve supervised learning? Important

10701 Semi supervised learning Can Unlabeled Data improve supervised learning? Important

10701 Semi supervised learning Can Unlabeled Data improve supervised learning? Important question! In many cases, unlabeled data is plentiful, labeled data expensive Image classification (x=images from the web, y=image type) Text

886 views • 37 slides
Learning to Extract Entities from Labeled and Unlabeled Text Rosie Jones Language Technologies

Learning to Extract Entities from Labeled and Unlabeled Text Rosie Jones Language Technologies

Learning to Extract Entities from Labeled and Unlabeled Text Rosie Jones Language Technologies Institute School of Computer Science Carnegie Mellon University May 5th, 2005 Extracting Information from Text Yesterday Rio de Janeiro was

1.05k views • 80 slides
Combining Labeled and Unlabeled Data in Statistical Natural Language Parsing Simon Fraser

Combining Labeled and Unlabeled Data in Statistical Natural Language Parsing Simon Fraser

Combining Labeled and Unlabeled Data in Statistical Natural Language Parsing Simon Fraser University April 18, 2002 Anoop Sarkar Department of Computer and Information Science University of Pennsylvania anoop@linc.cis.upenn.edu

567 views • 42 slides
Learning to Rank Learning to Rank with Partially-Labeled Data with Partially-Labeled Data Kevin

Learning to Rank Learning to Rank with Partially-Labeled Data with Partially-Labeled Data Kevin

Learning to Rank Learning to Rank with Partially-Labeled Data with Partially-Labeled Data Kevin Duh University of Washington (Joint work with Katrin Kirchhoff) 1 Motivation Motivation Machine learning can be an effective solution for

472 views • 29 slides
Visual Learning with Unlabeled Video and Look-Around Policies Kristen Grauman Department of

Visual Learning with Unlabeled Video and Look-Around Policies Kristen Grauman Department of

Visual Learning with Unlabeled Video and Look-Around Policies Kristen Grauman Department of Computer Science University of Texas at Austin Visual recognition: significant recent progress Big labeled Deep learning datasets ImageNet top-5

804 views • 52 slides
Learning to Rank with Learning to Rank with Partially-Labeled Data Partially-Labeled Data Kevin

Learning to Rank with Learning to Rank with Partially-Labeled Data Partially-Labeled Data Kevin

Learning to Rank with Learning to Rank with Partially-Labeled Data Partially-Labeled Data Kevin Duh University of Washington 1 The Ranking Problem The Ranking Problem Definition: Given a set of objects, sort them by preference. objectA

716 views • 59 slides
Expectation Maximization, and Learning from Partly Unobserved Data Recommended readings:

Expectation Maximization, and Learning from Partly Unobserved Data Recommended readings:

Expectation Maximization, and Learning from Partly Unobserved Data Recommended readings: Mitchell, Chapter 6.12 "Text Classification from Labeled and Unlabeled Documents using EM", K.Nigam, et al., 2000. Machine Learning, 39.

512 views • 37 slides
Introduction to Machine Learning ML-Basics: Data Learning goals 10 Understand structure of

Introduction to Machine Learning ML-Basics: Data Learning goals 10 Understand structure of

Introduction to Machine Learning ML-Basics: Data Learning goals 10 Understand structure of tabular data in ML 5 Understand difference between 0 y target and features 5 Understand difference between labeled and unlabeled data 10

670 views • 9 slides
Learning from Unlabeled Data INFO-4604, Applied Machine Learning University of Colorado Boulder

Learning from Unlabeled Data INFO-4604, Applied Machine Learning University of Colorado Boulder

Learning from Unlabeled Data INFO-4604, Applied Machine Learning University of Colorado Boulder December 5-7, 2017 Prof. Michael Paul Types of Learning Recall the definitions of: Supervised learning Most of the semester has been

611 views • 50 slides
Semi-Supervised Learning Maria-Florina Balcan 03/30/2015 Readings: Semi-Supervised Learning.

Semi-Supervised Learning Maria-Florina Balcan 03/30/2015 Readings: Semi-Supervised Learning.

Semi-Supervised Learning Maria-Florina Balcan 03/30/2015 Readings: Semi-Supervised Learning. Encyclopedia of Machine Learning. Jerry Zhu, 2010 Combining Labeled and Unlabeled Data with Co- Training. Avrim Blum, Tom Mitchell. COLT

953 views • 45 slides
Principal Component Analysis 4/7/17 PCA: the setting Unsupervised learning Unlabeled data

Principal Component Analysis 4/7/17 PCA: the setting Unsupervised learning Unlabeled data

Principal Component Analysis 4/7/17 PCA: the setting Unsupervised learning Unlabeled data Dimensionality reduction Simplify the data representation What does the algorithm do? Performs an affine change of basis. Rotate and

426 views • 16 slides
Principal Component Ananalysis 4-8-2016 PCA: the setting Unsupervised learning Unlabeled

Principal Component Ananalysis 4-8-2016 PCA: the setting Unsupervised learning Unlabeled

Principal Component Ananalysis 4-8-2016 PCA: the setting Unsupervised learning Unlabeled data Dimensionality reduction Simplify the data representation Change of basis examples so far Support vector machines Data that's not

423 views • 15 slides
Ac#ve Learning Aarti Singh Machine Learning 10-601 Dec 6, 2011 Slides Courtesy: Burr

Ac#ve Learning Aarti Singh Machine Learning 10-601 Dec 6, 2011 Slides Courtesy: Burr

Ac#ve Learning Aarti Singh Machine Learning 10-601 Dec 6, 2011 Slides Courtesy: Burr Settles, Rui Castro, Rob Nowak 1 Learning from unlabeled data Semi-supervised learning: Design a predictor based on iid unlabeled

738 views • 45 slides
K-Means Clustering 3/3/17 Unsupervised Learning We have a collection of unlabeled data

K-Means Clustering 3/3/17 Unsupervised Learning We have a collection of unlabeled data

K-Means Clustering 3/3/17 Unsupervised Learning We have a collection of unlabeled data points. We want to find underlying structure in the data. Examples: Identify groups of similar data points. Clustering Find a better basis

831 views • 14 slides
UnTran: Recognizing Unseen Activities with Unlabeled data using Transfer Learning ACM/IEEE

UnTran: Recognizing Unseen Activities with Unlabeled data using Transfer Learning ACM/IEEE

UnTran: Recognizing Unseen Activities with Unlabeled data using Transfer Learning ACM/IEEE IoTDI'18 April 18 th , 2018 Md Abdullah Al Hafiz Khan, Nirmalya Roy Challenges in Scaling Activity Recognition Cross User Diversity Device

451 views • 20 slides
GANs for Limited Labeled Data MIX+GAN Ian Goodfellow, Sta ff Research Scientist, Google Brain

GANs for Limited Labeled Data MIX+GAN Ian Goodfellow, Sta ff Research Scientist, Google Brain

Progressive GAN CoGAN LR-GAN MedGAN CGAN IcGAN A ff GAN DiscoGAN LS-GAN b-GAN LAPGAN MPM-GAN AdaGAN AMGAN iGAN LSGAN InfoGAN IAN CatGAN GANs for Limited Labeled Data MIX+GAN Ian Goodfellow, Sta ff Research Scientist, Google Brain

807 views • 26 slides
Active Semi-Supervised Learning using Submodular Functions Andrew Guillory, Jeff Bilmes

Active Semi-Supervised Learning using Submodular Functions Andrew Guillory, Jeff Bilmes

Active Semi-Supervised Learning using Submodular Functions Andrew Guillory, Jeff Bilmes University of Washington Given unlabeled data for example, a graph Learner chooses a labeled set Nature reveals labels y 0, 1 L - +

490 views • 28 slides
Clustering Aarti Singh Slides courtesy: Eric Xing Machine Learning 10-701/15-781 Oct 25, 2010

Clustering Aarti Singh Slides courtesy: Eric Xing Machine Learning 10-701/15-781 Oct 25, 2010

Clustering Aarti Singh Slides courtesy: Eric Xing Machine Learning 10-701/15-781 Oct 25, 2010 Unsupervised Learning Learning from unlabeled/ unannotated data (without supervision) Learning algorithm What can we predict from unlabeled

607 views • 32 slides
Clustering Clustering is an unsupervised classification method, i.e. unlabeled data is partitioned

Clustering Clustering is an unsupervised classification method, i.e. unlabeled data is partitioned

Clustering Clustering is an unsupervised classification method, i.e. unlabeled data is partitioned into subsets (clusters), according to a similarity measure, such thatsimilardata is grouped into the same cluster. Unlabeled Data

442 views • 22 slides
Learning the Structure of Generative Models without Labeled Data Stephen Bach Bryan He

Learning the Structure of Generative Models without Labeled Data Stephen Bach Bryan He

Learning the Structure of Generative Models without Labeled Data Stephen Bach Bryan He Alex Ratner Chris R Stanford University This Talk We study structure learning for generative models in which a latent variable

599 views • 33 slides
Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo

Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo

Active Learning with Active Learning with Model Selection Neil Rubens Sugiyama Lab / Tokyo Institute of Technology Active Learning (NLP Motivation) NLP (common scenario) Large amounts of unlabeled data Large amounts of unlabeled

706 views • 36 slides
Learning a Variable-Clustering Strategy for Octagon from Labeled Data Generated by a Static

Learning a Variable-Clustering Strategy for Octagon from Labeled Data Generated by a Static

1 Learning a Variable-Clustering Strategy for Octagon from Labeled Data Generated by a Static Analysis Kihong Heo 1 , Hakjoo Oh 2 , Hongseok Yang 3 Seoul National University 1 Korea University 2 University of Oxford 3 SAS 2016 @Edinburgh 2

823 views • 32 slides
Word2Vec Michael Collins, Columbia University Motivation We can easily collect very large

Word2Vec Michael Collins, Columbia University Motivation We can easily collect very large

Word2Vec Michael Collins, Columbia University Motivation We can easily collect very large amounts of unlabeled text data Can we learn useful representations (e.g., word embeddings) from unlabeled data? Bigrams from Unlabeled Data

254 views • 6 slides

More recommend