-
LearnGet Started
Run PyTorch locally or get started quickly with one of the supported cloud platforms
TutorialsWhats new in PyTorch tutorials
Learn the BasicsFamiliarize yourself with PyTorch concepts and modules
PyTorch RecipesBite-size, ready-to-deploy PyTorch code examples
Intro to PyTorch - YouTube SeriesMaster PyTorch basics with our engaging YouTube tutorial series
-
EcosystemTools
Learn about the tools and frameworks in the PyTorch Ecosystem
CommunityJoin the PyTorch developer community to contribute, learn, and get your questions answered.
ForumsA place to discuss PyTorch code, issues, install, research
Developer ResourcesFind resources and get questions answered
Contributor Awards - 2024Award winners announced at this year's PyTorch Conference
-
Blog & NewsPyTorch Blog
Catch up on the latest technical news and happenings
Community BlogStories from the PyTorch ecosystem
VideosLearn about the latest PyTorch tutorials, new, and more
Community StoriesLearn how our community solves real, everyday machine learning problems with PyTorch
EventsFind events, webinars, and podcasts
NewsletterStay up-to-date with the latest updates
- Become a Member
-
X
Multi-Modal Tabular Deep Learning with PyTorch Frame
Date: February 19, 12 pm PST
Speaker: Akihiro Nitta, Software Engineer, Kumo.ai
Link to session video
Download slides
In this talk, Akihiro introduced PyTorch Frame, a modular framework for multi-modal tabular deep learning. PyTorch Frame enables seamless integration with the PyTorch ecosystem, including PyTorch Geometric for graph-based message passing across relational data and Hugging Face Transformers for extracting rich text features. The talk also highlights its specialized data structures for efficiently handling sparse features, making PyTorch Frame an essential tool for modern tabular data.
Akihiro Nitta is a software engineer on the ML team at Kumo.ai and a core contributor to PyTorch Frame and PyTorch Geometric, with prior experience as a maintainer of PyTorch Lightning.
