learning generative models across incomparable spaces
play

LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot - PowerPoint PPT Presentation

Feb 26, 2024 •112 likes •250 views

LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David Alvarez-Melis, Andreas Krause, Stefanie Jegelka Pos oster #173 173 Poster #173 173 & Charlotte Bunne Generative Modeling generative = network

  1. LEARNING GENERATIVE MODELS ACROSS INCOMPARABLE SPACES Cha harlot otte Bunne unne , David Alvarez-Melis, Andreas Krause, Stefanie Jegelka Pos oster #173 173 Poster #173 173 & Charlotte Bunne

  2. Generative Modeling generative = network data noise P x … … Poster #173 173 & Charlotte Bunne

  3. Beyond Identical Generation ... generative ? network data noise P x … … … enf nfor orce style. Poster #173 173 & Charlotte Bunne

  4. Beyond Identical Generation ... generative ? network data noise P x … … … learn n acros oss di different nt di dimens nsions ons. Poster #173 173 & Charlotte Bunne

  5. Beyond Identical Generation ... generative graph ? network data noise P x y … … x … trans nslate be between n repr present ntation. on. Poster #173 173 & Charlotte Bunne

  6. Beyond Identical Generation ... generative ? network data z noise P x y … … y x x … learn n mani nifol olds ds. Poster #173 173 & Charlotte Bunne

  7. . Challenges generative network ? E data e z noise P x y … … y x x How to compare samples from incomparable spaces? 1 . . . … learn n mani nifol olds ds. What should be preserved? What can we modify? 2 How to stabilize learning despite additional freedom? 3 Poster #173 173 & Charlotte Bunne

  8. Learning Generative Models Optimal Transpor ort Distances L ( y i , x l ) generative y i network y j x l y h x m noise P x … … x k L ( y j , x k ) ... distance between distributions : mini nimal cos ost of transporting mass between them. n T . ... find an opt optimal trans nspor port pl plan … classical Wasserstein distances assume that spaces are com ompa parabl ble ! Poster #173 173 & Charlotte Bunne

  9. . <latexit sha1_base64="5dO7VeWeQwCDzXJsk/Ifg7of+5Q=">AB6XicbVDLSgNBEOyNrxhfUY9eBoPgKezGgB4DgniMYh6QLGF2MpsMmZ1dZnqFsAT8AC8eFPHqH3nzb5w8DpY0FBUdPdFSRSGHTdbye3tr6xuZXfLuzs7u0fFA+PmiZONeMNFstYtwNquBSKN1Cg5O1EcxoFkreC0fXUbz1ybUSsHnCcD+iAyVCwSha6b6b9Yolt+zOQFaJtyAlWKDeK351+zFLI6QSWpMx3MT9DOqUTDJ4VuanhC2YgOeMdSRSNu/Gx26YScWaVPwljbUkhm6u+JjEbGjKPAdkYUh2bZm4r/eZ0Uwys/EypJkSs2XxSmkmBMpm+TvtCcoRxbQpkW9lbChlRThjacg3BW35lTQrZe+iXLmrlmo3T/M48nACp3AOHlxCDW6hDg1gEMIzvMKbM3JenHfnY96acxYRHsMfOJ8/xAaN7Q=</latexit> <latexit sha1_base64="5dO7VeWeQwCDzXJsk/Ifg7of+5Q=">AB6XicbVDLSgNBEOyNrxhfUY9eBoPgKezGgB4DgniMYh6QLGF2MpsMmZ1dZnqFsAT8AC8eFPHqH3nzb5w8DpY0FBUdPdFSRSGHTdbye3tr6xuZXfLuzs7u0fFA+PmiZONeMNFstYtwNquBSKN1Cg5O1EcxoFkreC0fXUbz1ybUSsHnCcD+iAyVCwSha6b6b9Yolt+zOQFaJtyAlWKDeK351+zFLI6QSWpMx3MT9DOqUTDJ4VuanhC2YgOeMdSRSNu/Gx26YScWaVPwljbUkhm6u+JjEbGjKPAdkYUh2bZm4r/eZ0Uwys/EypJkSs2XxSmkmBMpm+TvtCcoRxbQpkW9lbChlRThjacg3BW35lTQrZe+iXLmrlmo3T/M48nACp3AOHlxCDW6hDg1gEMIzvMKbM3JenHfnY96acxYRHsMfOJ8/xAaN7Q=</latexit> Defining a Distance Across Different Spaces 1 Gromov-Wasserstein Discrepancy intra-space distances L ( D hi , D lm ) generative y i D lm network D hi y j D kl x l y h x m D ij noise P x … … x k L ( D ij , D kl ) ) := { tot otal discrepancy { GW ( D, ¯ L ( D ik , ¯ � D ) := min D jl ) T ij T kl of pairwise distances of Definition on : T acros oss dom omains ijkl optimal intra-space transport plan distances Poster #173 173 & Charlotte Bunne

  10. Gromov-Wasserstein Generative Model (GW GAN) D noise GW … . … … … . . D generator adversary . . . g ! ( z ) = y data f ⍵ ( � ) Poster #173 173 & Charlotte Bunne

  11. Flexibility of the Model . 2 … recovers geometrical properties of the target distribution, … but global aspects are undetermined style adversary sha hape pe the he ge gene nerated d di distribut bution on via de design gn cons onstraint nts GW GAN … … Poster #173 173 & Charlotte Bunne

  12. Flexibility of the Model . 2 … recovers geometrical properties of the target distribution, … but global aspects are undetermined style . . adversary sha hape pe the he ge gene nerated d di distribut bution on via de design gn cons onstraint nts 3 GW GAN … … … adversary can arbitrarily samples in generated samples in data samples in generator ge or space feature space fe fe feature space … distort the space f ω ( g θ ( Z )) f ω ( X ) g θ ( Z ) regul gularize adv dversary by by enf nfor orcing ng it to o de define ne unitary trans uni nsfor ormations ons Poster #173 173 & Charlotte Bunne

  13. Gromov-Wasserstein Generative Model By utilizing the Grom omov ov-Wa Wasser erstei tein discrepancy we disentangle data and ` generator space. This enables us to learn ge generative mod odels acros oss different data types and space ` dimension ons and sh shape the generated distributions with design constraints. Pos oster #173 173 More details, tonight at Poster #173 173 & Charlotte Bunne

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

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
Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures

Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures

Introduction to Generative Models (and GANs) Haoqiang Fan fhq@megvii.com Nov. 2017 Figures adapted from NIPS 2016 Tutorial Generative Adversarial Networks Generative Models: Learning the Distributions Discriminative: learns the likelihood

1.37k views • 77 slides
Adversarial BoltzmannMachines Belief Nets Networks Variational NADE

Adversarial BoltzmannMachines Belief Nets Networks Variational NADE

Unsupervised Learning Non-probabilistic Models Probabilistic Sparse Coding (Generative) Models Autoencoders Others (e.g. k-means) Tractable Models Non-Tractable Models Generative Fully observed Adversarial

815 views • 58 slides
THE INCOMPARABLE Incomparable A concept that is unique in every way since 1990 # A concept you

THE INCOMPARABLE Incomparable A concept that is unique in every way since 1990 # A concept you

THE INCOMPARABLE Incomparable A concept that is unique in every way since 1990 # A concept you will not find Objectif ? anywhere else in the world One of a kind since its creation in 1990, the Rallye Acha des Gazelles du Maroc is

479 views • 33 slides
Classification with generative models 2 DSE 210 Classification with parametrized models

Classification with generative models 2 DSE 210 Classification with parametrized models

Classification with generative models 2 DSE 210 Classification with parametrized models Classifiers with a fixed number of parameters can represent a limited set of functions. Learning a model is about picking a good approximation. Typically the

427 views • 39 slides
Learning Deep Generative Models Inference &amp; Representation Lecture 12 Rahul G. Krishnan

Learning Deep Generative Models Inference &amp; Representation Lecture 12 Rahul G. Krishnan

Introduction Variational Inference Deep Generative Models Summary Learning Deep Generative Models Inference &amp; Representation Lecture 12 Rahul G. Krishnan Fall 2015 Rahul G. Krishnan Learning Deep Generative Models Introduction

1.22k views • 83 slides
Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is

Generative Adversarial Nets(GANs) Troy Cary and Chenzhi Zhao A generative adversarial net is a type of neural net, used in deep learning/machine learning problems The goal of a GAN is to train two simultaneous models: a generative model

441 views • 18 slides
LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning

LAB MEETING: A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning and Energy-Based models Suwon Suh POSTECH MLG Feb, 13, 2017 Goal Understanding Basic Models 1) Generative Adversarial Networks (GAN) 2)

722 views • 12 slides
Outline Latent Variable Generative Models Cooperative Vector Quantizer Model Model

Outline Latent Variable Generative Models Cooperative Vector Quantizer Model Model

2/4/2020 CS 3750 Advanced Machine Learning Latent Variable Generative Models II Ahmad Diab AHD23@cs.pitt.edu Feb 4, 2020 Based on slides of Professor Milos Hauskrecht Outline Latent Variable Generative Models Cooperative Vector

435 views • 20 slides
Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes &amp; George

Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes &amp; George

Learning Universal Adversarial Perturbations with Generative Models Jamie Hayes &amp; George Danezis UCL Adversarial examples transfer between different models. An adversarial example crafted against one model will generally fool other models.

515 views • 18 slides
Variational Inference and Generative Models CS 294-112: Deep Reinforcement Learning Sergey

Variational Inference and Generative Models CS 294-112: Deep Reinforcement Learning Sergey

Variational Inference and Generative Models CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 3 due next Wednesday 2. Accept CMT peer review invitations These are required (part of your final project grade)

652 views • 34 slides
Computational Systems Biology Deep Learning in the Life Sciences 6.802 6.874 20.390 20.490

Computational Systems Biology Deep Learning in the Life Sciences 6.802 6.874 20.390 20.490

Computational Systems Biology Deep Learning in the Life Sciences 6.802 6.874 20.390 20.490 HST.506 David Gifford Lecture 9 March 5, 2020 Generative Models http://mit6874.github.io 1 Why generative models? We can sample new examples from a

747 views • 52 slides
Machine Learning - MT 2017 10. Classification : Generative Models Varun Kanade University of

Machine Learning - MT 2017 10. Classification : Generative Models Varun Kanade University of

Machine Learning - MT 2017 10. Classification : Generative Models Varun Kanade University of Oxford October 30, 2017 Recap: Supervised Learning - Regression Discriminative Model: Linear Model (with Gaussian noise) p ( y | w , x ) = w x + N

837 views • 31 slides
Semi-supervised Learning with Deep Generative Models Diedrik P. Kingma, Danilo J. Rezende, Shakir

Semi-supervised Learning with Deep Generative Models Diedrik P. Kingma, Danilo J. Rezende, Shakir

Semi-supervised Learning with Deep Generative Models Diedrik P. Kingma, Danilo J. Rezende, Shakir Mohamed, Max Welling What is Deep Learning very good at? Classifying highly structured data -ImageNet -Part of Speech Tagging -MNIST

195 views • 18 slides
CS 6316 Machine Learning Generative Models Yangfeng Ji Department of Computer Science

CS 6316 Machine Learning Generative Models Yangfeng Ji Department of Computer Science

CS 6316 Machine Learning Generative Models Yangfeng Ji Department of Computer Science University of Virginia Basic Definition Data generation process An idealized process to illustrate the relations among domain set X , label set Y , and the

1.13k views • 101 slides
Probabilistic Models of Cognition: Generative models Table of Contents Chapter

Probabilistic Models of Cognition: Generative models Table of Contents Chapter

Probabilistic Models of Cognition: Generative models Table of Contents Chapter Content Generative Model Example: Plinko Machine Working Model can be used captures some for simulation structure of the world in useful way

825 views • 78 slides
Who you gonna call? Navigating Complex Discrimination and Retaliation Issues on Campus Ms.

Who you gonna call? Navigating Complex Discrimination and Retaliation Issues on Campus Ms.

Who you gonna call? Navigating Complex Discrimination and Retaliation Issues on Campus Ms. Congeniality? Professor X has been a faculty member with the department for many years. She has always had difficulty working well with others but over

410 views • 11 slides
Connect With Us! @ji_org 980-222-1078 (call or text) @justiceinitiatives outreach@

Connect With Us! @ji_org 980-222-1078 (call or text) @justiceinitiatives outreach@

Connect With Us! @ji_org 980-222-1078 (call or text) @justiceinitiatives outreach@ /justiceinitiatives justiceinitiatives.org #NCJusticeSummit WELCOME OPENING REMARKS Scott Harris Justice Initiatives INTRODUCTION OF SPECIAL GUESTS

702 views • 27 slides
Database Programming Joan Boone jpboone@email.unc.edu Summer 2020 Slide 1 Topics Part 1

Database Programming Joan Boone jpboone@email.unc.edu Summer 2020 Slide 1 Topics Part 1

INLS 560 Programming for Information Professionals Database Programming Joan Boone jpboone@email.unc.edu Summer 2020 Slide 1 Topics Part 1 Database overview Basic SQL Part 2 SQLite introduction DB Browser for SQLite

636 views • 39 slides
CREA CREATE TE IT IT MAKE IT MAKE IT MO MOVE IT VE IT How we got where we are and

CREA CREATE TE IT IT MAKE IT MAKE IT MO MOVE IT VE IT How we got where we are and

ENVISIONING CHARLOTTE 2030: EAST COAST GLOBAL COMMERCIAL CENTER CREA CREATE TE IT IT MAKE IT MAKE IT MO MOVE IT VE IT How we got where we are and where were going! 250 years of business in Charlotte 1762 - 2012 From this (

496 views • 20 slides
Qwickly Attendance and Tools Webinar June 18, 2019 Academic Computing Services Summer Webinar

Qwickly Attendance and Tools Webinar June 18, 2019 Academic Computing Services Summer Webinar

Qwickly Attendance and Tools Webinar June 18, 2019 Academic Computing Services Summer Webinar Series Academic Computing Services Webinar Facilitator: Allan Winter Academic Computing Coordinator Webinar Presenter: Charlotte Russell Cox

777 views • 39 slides
Wall Street, Main Street, Your Street: How Investors Impact the Single-Family Housing Market Sean

Wall Street, Main Street, Your Street: How Investors Impact the Single-Family Housing Market Sean

Wall Street, Main Street, Your Street: How Investors Impact the Single-Family Housing Market Sean Brunson, Richard Buttimer Jr. University of North Carolina at Charlotte May 2020 Home Price Indices 140 130 120 CaseShiller 110 Zillow

1.08k views • 30 slides
Live Streaming for the Long Haul A little about me Rev. Brian Wallace Associate Minister to

Live Streaming for the Long Haul A little about me Rev. Brian Wallace Associate Minister to

Live Streaming for the Long Haul A little about me Rev. Brian Wallace Associate Minister to Pittsburgh Presbytery Three Key Points Live streaming is complicated and multi-faceted, with numerous ways it can go wrong - even if it worked

480 views • 7 slides
CDSS Web Chat #3 on 1/16/19 Increasing Youth Involvement Having trouble with your computer audio?

CDSS Web Chat #3 on 1/16/19 Increasing Youth Involvement Having trouble with your computer audio?

CDSS Web Chat #3 on 1/16/19 Increasing Youth Involvement Having trouble with your computer audio? Dial in: +1 646-558-8656 Web Chat Format 8:30 pm EDT Introduction: Katy German and Linda Henry 8.35 pm Web Chat Guests:

288 views • 9 slides

More recommend