data valuation using reinforcement learning
play

Data Valuation using Reinforcement Learning Jinsung Yoon, Sercan O. - PowerPoint PPT Presentation

Feb 01, 2023 •299 likes •528 views

Data Valuation using Reinforcement Learning Jinsung Yoon, Sercan O. Arik, Tomas Pfister Google Cloud AI 2020 International Conference on Machine Learning (ICML 2020) 1 Problem Defjnition What is data valuation? How much does each

  1. Data Valuation using Reinforcement Learning Jinsung Yoon, Sercan O. Arik, Tomas Pfister Google Cloud AI 2020 International Conference on Machine Learning (ICML 2020) 1

  2. Problem Defjnition What is data valuation? ● ○ How much does each data contribute to the trained model 2 Amirata Ghorbani, James Y. Zou, Data Shapley: Equitable Valuation of Data for Machine Learning , ICML , 2019

  3. Objective & Use-cases - Learn in reliable way Data valuation ● Fair valuation for the labelers and data provider ○ Insights about the dataset ○ 3 Ruoxi Jia et al., Towards Efficient Data Valuation Based on the Shapley Value , AISTATS , 2019

  4. Objective & Use-cases - Learn in reliable way High-value samples Corrupted sample discovery ● Low-value samples 4

  5. Objective & Use-cases - Learn in reliable way Robust learning with noisy (or cheaply-acquired) datasets ● Augmented learning ○ Cheaply-acquired samples High valued samples 5 Amirata Ghorbani, James Y. Zou, Data Shapley: Equitable Valuation of Data for Machine Learning , ICML , 2019

  6. Objective & Use-cases - Learn in reliable way Domain adaptation ● Assigns higher values on the samples from the target distribution ○ Training Set Target Set Type Type A B Type D Type Type C D High valued samples 6

  7. Related works - Leave-one-out Not reasonable when there are two similar training samples. ● 7 Amirata Ghorbani, James Y. Zou, Data Shapley: Equitable Valuation of Data for Machine Learning , ICML , 2019

  8. Related works - Data Shapley Computational complexity is exponential with the number of samples. ● 8 Amirata Ghorbani, James Y. Zou, Data Shapley: Equitable Valuation of Data for Machine Learning , ICML , 2019

  9. Challenges & Motivation ● The search space is extremely large. ○ Impossible to explore the entire space. ● Training processes can be non-differentiable ○ Selection operation (i.e. sampler block) is non-differentiable. ○ Performance metrics can be non-differentiable (accuracy, AUC). End-to-end back-propagation may not be possible. ○ Reinforcement learning is an efficient way to explore large search ● space and to handle non-differentiable process. 9

  10. High-level fjgure for DVRL ● Jointly train selector and predictor in an end-to-end way. 10

  11. Problem formulation To minimize the validation loss Components ● Weighted optimization for ○ Training set: predictor ○ Validation set: ○ Predictor model: ○ Data valuation model: 11

  12. Block diagram 12

  13. Experiments - How to quantitatively evaluate the data valuation? Remove high / low valued samples ● Corrupted sample discovery ● Robust learning with noisy data ● Domain adaptation ● 13

  14. Results - Remove high / low valued samples Standard supervised learning setting (train, validation, test datasets ● come from the same distribution) Remove high valued samples: Fastest performance degradation ● Remove low valued samples: Slowest performance degradation ● 14

  15. Results - Corrupted sample discovery Corrupted sample setting (20% of label noise) ● ● Highest True Positive Rate (TPR) for corrupted sample discovery 15

  16. Results - Robust learning with noisy labels (40%) Proves scalability of DVRL in terms of complex models ● (WideResNet-28-10 and ResNet-32) and large datasets (CIFAR) State-of-the-art robust learning performance ● Mengye Ren et al., Learning to Reweight Examples for Robust Deep Learning , ICML , 2018 16

  17. Results - Domain adaptation on Retail dataset Training Set Train-on-Specific Training Set Testing Set Type D Type Type Train-on-All A B Type D Train-on-Rest Type Type C D Training Set Type A Type Type B C 17

  18. Results - Domain adaptation on Retail dataset Significant gain on Train on Rest setting ( largest domain mismatch ) ● ● Reasonable gain on Train on All setting ( most common setting ) ● Marginal gain on Train on Specific setting ( no domain mismatch ) 18

  19. Results - Domain adaptation in other domains Main source of gain: ● ○ DVRL jointly optimizes the data valuator and corresponding predictor model 19 Amirata Ghorbani, James Y. Zou, Data Shapley: Equitable Valuation of Data for Machine Learning , ICML , 2019

  20. Discussion: How many validation samples are needed? ● A small number of validation samples are enough for DVRL training. Reasonable performances even with 10 validation samples on Adult data. ● 20

  21. Codebase of DVRL DVRL - Github: https://github.com/google-research/google-research/tree/master/dvrl DVRL- AI-Hub: https://aihub.cloud.google.com/u/0/p/products%2Fcb6b588c-1582-4868-a944-dc70ebe61a36 21

Recommend

RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem

Introduction to Reinforcement Learning RL Overview of topics About Reinforcement Learning The Reinforcement Learning Problem Inside an RL agent Temporal difference learning Many faces of Reinforcement Learning What is

551 views • 35 slides
Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine

Reinforcement Learning Reinforcement Learning Reinforcement Learning in a nutshell g Imagine playing a new game whose rules you dont know; after a hundred or so moves your don t know; after a hundred or so moves, your opponent announces, You

511 views • 30 slides
Iroko A Data Center Emulator for Reinforcement Learning Fabian Ruffy, Michael Przystupa, Ivan

Iroko A Data Center Emulator for Reinforcement Learning Fabian Ruffy, Michael Przystupa, Ivan

Iroko A Data Center Emulator for Reinforcement Learning Fabian Ruffy, Michael Przystupa, Ivan Beschastnikh University of British Columbia https://github.com/dcgym/iroko Reinforcement Learning and Networking 2 Reinforcement Learning and

722 views • 28 slides
Reinforcement Learning You can think of supervised learning as the teacher providing answers

Reinforcement Learning You can think of supervised learning as the teacher providing answers

Reinforcement Learning You can think of supervised learning as the teacher providing answers (the class labels) Reinforcement learning: In reinforcement learning, the agent learns Markov Decision Processes based on a punishment/reward

89 views • 6 slides
Examples of Reinforcement Learning Robocup Soccer Teams Stone & Veloso, Reidmiller et al.

Examples of Reinforcement Learning Robocup Soccer Teams Stone & Veloso, Reidmiller et al.

Reinforcement Learning Slides by Rich Sutton Mods by Dan Lizotte Refer to Reinforcement Learning: An Introduction by Sutton and Barto Alpaydin Chapter 16 Up until now we have been Supervised Learning Classifying, mostly

891 views • 31 slides
Lecture 14: Introduction to Reinforcement Learning CS109B Data Science 2 Pavlos Protopapas and

Lecture 14: Introduction to Reinforcement Learning CS109B Data Science 2 Pavlos Protopapas and

Lecture 14: Introduction to Reinforcement Learning CS109B Data Science 2 Pavlos Protopapas and Mark Glickman Outline What is Reinforcement Learning RL Formalism 1. Reward 2. The agent 3. The environment 4. Actions 5.

1.27k views • 64 slides
Control Regularization for Reduced Variance Reinforcement Learning Richard Cheng, Abhinav Verma,

Control Regularization for Reduced Variance Reinforcement Learning Richard Cheng, Abhinav Verma,

Control Regularization for Reduced Variance Reinforcement Learning Richard Cheng, Abhinav Verma, Gabor Orosz, Swarat Chaudhuri Yisong Yue, Joel W. Burdick Reinforcement Learning Reinforcement learning (RL) studies how to use data from

204 views • 9 slides
CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning

CS885 Reinforcement Learning Module 2: June 6, 2020 Maximum Entropy Reinforcement Learning Haarnoja, Tang et al. (2017) Reinforcement Learning with Deep Energy Based Policies, ICML . Haarnoja, Zhou et al. (2018) Soft Actor-Critic: Off-Policy

682 views • 24 slides
Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control

Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control

Reinforcement Learning Reinforcement Learning Now that you know a little about Optimal Control Theory, you actually have some knowledge in RL. RL shares the overall goal with OCT: solving for a control policy such that the cumulative cost

610 views • 22 slides
Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning II Still assume a Marko kov decision process (MDP): A se set o of st states s s S A se set o of a actions ( s (per st state) A A mo model

96 views • 5 slides
R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec

R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec

R i f R i f Reinforcement Learning III Reinforcement Learning III t L t L i i III III Dec 03 2008 1 Large State Spaces h When a problem has a large state space we can not longer represent the U or Q functions as explicit tables explicit

436 views • 18 slides
Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning?

Reinforcement Learning<br/><br/> 4/25/19, 8*06 PM Reinforcement Learning<br/><br/> 4/25/19, 8*06 PM Reinforcement Learning UMaine COS 470/570 Introduction to AI Why reinforcement learning? Spring 2019 Created:

371 views • 15 slides
7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B.

7. Motor Control and Reinforcement Learning Outline A. Action Selection and Reinforcement B. Temporal Difference Reinforcement Learning C. PVLV Model D. Cerebellum and Error-driven Learning 2/23/18 COSC 494/594 CCN 2 Sensory-Motor Loop

790 views • 56 slides
Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree

Deep Reinforcement Learning [Mastering the Game of Go with Deep Reinforcement Learning and Tree Search, Nature 2016] CS 486/686 University of Waterloo Lecture 21: July 12, 2017 Outline AlphaGo Supervised Learning of Policy Networks

540 views • 15 slides
Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi

Reinforcement Learning CS 4100: Artificial Intelligence Reinforcement Learning Ja Jan-Wi Willem van de Meent Northeastern University [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188

145 views • 10 slides
Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning:

Reinforcement Learning Reinforcement Learning AIMA Chapters: 21.1, 21.2, 21.3. Sutton and Barto, Reinforcement Learning: an Introduction, 2nd Edition: Chapters 6 (6.1 6.5) Outline Reinforcement Learning Reinforcement Learning: the

587 views • 27 slides
Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and

Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and

Module 11 Introduction to Reinforcement Learning CS 886 Sequential Decision Making and Reinforcement Learning University of Waterloo Machine Learning Supervised Learning Teacher tells learner what to remember Reinforcement Learning

401 views • 29 slides
Machine Learning and Data Mining Reinforcement Learning Markov Decision Processes Kalev Kask

Machine Learning and Data Mining Reinforcement Learning Markov Decision Processes Kalev Kask

+ Machine Learning and Data Mining Reinforcement Learning Markov Decision Processes Kalev Kask Overview Intro Markov Decision Processes Reinforcement Learning Sarsa Q-learning Exploration vs Exploitation tradeoff 2

1.81k views • 146 slides
1 Pure Reinforcement Learning vs. Reinforcement Learning Monte-Carlo Planning No knowledge

1 Pure Reinforcement Learning vs. Reinforcement Learning Monte-Carlo Planning No knowledge

CSE 573: Artificial Intelligence Todo Reinforcement Learning Add simulations from 473 Dan Weld Add UCB bound (cut bolzman & constant epsilon Add snazzy videos (pendulum, zico kolter See http://www See http://www-

462 views • 11 slides
Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest

Safe Reinforcement Learning Philip S. Thomas Stanford CS234: Reinforcement Learning, Guest Lecture May 24, 2017 Lecture overview What makes a reinforcement learning algorithm safe ? Notation Creating a safe reinforcement learning

1.42k views • 88 slides
Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5

Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5

1 Reinforcement Learning Framework Reinforcement Learning Rewards, Returns Lectures 4 and 5 Environment Dynamics Gillian Hayes Components of a Problem 18th January 2007 Values and Action Values, V and Q Optimal Policies

109 views • 7 slides
Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007

Introduction to Reinforcement Learning Bayesian Methods in Reinforcement Learning ICML 2007 sequential decision making under uncertainty ? How Can I ... ? Move around in the physical world (e.g. driving, navigation) Play and win a game

519 views • 21 slides
Optimizing Federated Learning on Non-IID Data with Reinforcement Learning Hao Wang *, Zakhary

Optimizing Federated Learning on Non-IID Data with Reinforcement Learning Hao Wang *, Zakhary

INFOCOM20 Optimizing Federated Learning on Non-IID Data with Reinforcement Learning Hao Wang *, Zakhary Kaplan*, Di Niu^, Baochun Li* *University of Toronto, ^University of Alberta < < > > Alexa Siri 2 Machine

541 views • 53 slides
reinforcement learning through the optimization lens Benjamin Recht University of California,

reinforcement learning through the optimization lens Benjamin Recht University of California,

reinforcement learning through the optimization lens Benjamin Recht University of California, Berkeley trustable, scalable, predictable Control Theory ! Reinforcement Learning is the study of how to use past data to enhance the future

1.03k views • 74 slides

More recommend