Title: [2410.06424] Restructuring Vector Quantization with the Rotation Trick
Description: Abstract page for arXiv paper 2410.06424: Restructuring Vector Quantization with the Rotation Trick
Keywords: No keywords
Text content: [2410.06424] Restructuring Vector Quantization with the Rotation Trick                                         Skip to main content      We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate       > cs > arXiv:2410.06424         Help | Advanced Search     All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text     Search                open search       GO    open navigation menu   quick links  Login Help Pages About             Computer Science > Machine Learning   arXiv:2410.06424 (cs)            [Submitted on 8 Oct 2024] Title:Restructuring Vector Quantization with the Rotation Trick Authors:Christopher Fifty, Ronald G. Junkins, Dennis Duan, Aniketh Iger, Jerry W. Liu, Ehsan Amid, Sebastian Thrun, Christopher Ré View a PDF of the paper titled Restructuring Vector Quantization with the Rotation Trick, by Christopher Fifty and 7 other authors View PDF HTML (experimental)  Abstract:Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often referred to as the codebook -- and quantizing each encoder output to the nearest vector in the codebook. However, as vector quantization is non-differentiable, the gradient to the encoder flows around the vector quantization layer rather than through it in a straight-through approximation. This approximation may be undesirable as all information from the vector quantization operation is lost. In this work, we propose a way to propagate gradients through the vector quantization layer of VQ-VAEs. We smoothly transform each encoder output into its corresponding codebook vector via a rotation and rescaling linear transformation that is treated as a constant during backpropagation. As a result, the relative magnitude and angle between encoder output and codebook vector becomes encoded into the gradient as it propagates through the vector quantization layer and back to the encoder. Across 11 different VQ-VAE training paradigms, we find this restructuring improves reconstruction metrics, codebook utilization, and quantization error. Our code is available at this https URL.         Subjects:  Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)  Cite as: arXiv:2410.06424 [cs.LG]     (or  arXiv:2410.06424v1 [cs.LG] for this version)                 https://doi.org/10.48550/arXiv.2410.06424   Focus to learn more                      arXiv-issued DOI via DataCite        Submission history From: Christopher Fifty [view email]       [v1]         Tue, 8 Oct 2024 23:39:34 UTC (4,230 KB)       Full-text links: Access Paper:   View a PDF of the paper titled Restructuring Vector Quantization with the Rotation Trick, by Christopher Fifty and 7 other authorsView PDFHTML (experimental)TeX SourceOther Formats view license        Current browse context: cs.LG   < prev    |    next >   new  |  recent  | 2024-10      Change to browse by:      cs cs.CV     References & Citations  NASA ADSGoogle Scholar Semantic Scholar     a export BibTeX citation Loading...     BibTeX formatted citation ×   loading...   Data provided by:      Bookmark            Bibliographic Tools  Bibliographic and Citation Tools       Bibliographic Explorer Toggle    Bibliographic Explorer (What is the Explorer?)        Connected Papers Toggle    Connected Papers (What is Connected Papers?)       Litmaps Toggle    Litmaps (What is Litmaps?)        scite.ai Toggle    scite Smart Citations (What are Smart Citations?)          Code, Data, Media  Code, Data and Media Associated with this Article       alphaXiv Toggle    alphaXiv (What is alphaXiv?)        Links to Code Toggle    CatalyzeX Code Finder for Papers (What is CatalyzeX?)        DagsHub Toggle    DagsHub (What is DagsHub?)        GotitPub Toggle    Gotit.pub (What is GotitPub?)        Huggingface Toggle    Hugging Face (What is Huggingface?)        Links to Code Toggle    Papers with Code (What is Papers with Code?)        ScienceCast Toggle    ScienceCast (What is ScienceCast?)              Demos  Demos       Replicate Toggle    Replicate (What is Replicate?)        Spaces Toggle    Hugging Face Spaces (What is Spaces?)        Spaces Toggle    TXYZ.AI (What is TXYZ.AI?)         Related Papers  Recommenders and Search Tools       Link to Influence Flower    Influence Flower (What are Influence Flowers?)        Core recommender toggle    CORE Recommender (What is CORE?)        IArxiv recommender toggle    IArxiv Recommender (What is IArxiv?)       Author Venue Institution Topic                      About arXivLabs           arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.           Which authors of this paper are endorsers? |     Disable MathJax (What is MathJax?)                  About Help      contact arXivClick here to contact arXiv  Contact   subscribe to arXiv mailingsClick here to subscribe  Subscribe            Copyright Privacy Policy     Web Accessibility Assistance   arXiv Operational Status                      Get status notifications via                     email                     or slack