Akihiro Nitta

🚀 New tutorial on Graph Transformers! We introduce a powerful architecture combining the strengths of GNNs and Transformers for structured data. Learn how GTs open new possibilities for graph learning. kumo.ai/research/intro… #GraphTransformers #MachineLearning #AI #GNN

Register for tomorrow's expert exchange webinar where Akihiro Nitta (hubs.la/Q037b-7j0) will introduce #PyTorch Frame, a modular framework for multi-modal tabular #deeplearning. See how it integrates with PyTorch Geometric and Hugging Face Transformers to enhance relational…

Introducing the new Kumo platform: Build predictive and embedding models directly on your relational data — without feature engineering. Go from predictive modeling to predictive AI. hubs.ly/Q035xfgP0

Humbled and honored to be recognized at @NeurIPSConf for our work on PyTorch Frame: github.com/pyg-team/pytor… Creating this open-source framework from scratch has been an incredible journey, and I’m deeply grateful to the amazing team I had the privilege to work with. 🌟

Excited to share our work from Kumo. We innovated and built a very strong GNN model for recommendation, which is at the core of Kumo recommender systems.

🎉 Excited to announce the release of ContextGNN, our state-of-art and scalable recommendation model from Kumo! 🔗 ContextGNN paper: arxiv.org/abs/2411.19513 What makes ContextGNN unique? It combines pair-wise and two-tower representations into a single architecture, enabling…

💠 Stanford Graph Learning Workshop 2024! Join leaders from academia and industry to explore the latest in Machine Learning and AI. Topics include Relational domains, Foundation Models, Agents and more. Save the date: Tuesday, Nov 5, 2024, 09:00 - 18:00 PT. The event will be…

🚀 PyG 2.6 is here: GNNs + LLMs, PyTorch 2.4 and more! 🎉 We’re excited to announce the release of PyG 2.6.0, packed with incredible updates for graph learning! Here’s a quick rundown of what’s new: ✨ Key Highlights: -- GNNs + LLMs: New models like GRetriever that co-train…

PyG 2.6 is here, including new models and examples on how to combine GNNs with LLMs! Thanks to many contributors who have made this release possible. Full release notes👇 github.com/pyg-team/pytor…

Check out our PyTorch Frame tech report arxiv.org/abs/2404.00776 We aim to push tabular deep learning to handle complex multi-modal, multi-tabular data, beyond conventional single-tabular data. We do so by seamlessly integrating PyTorch Frame with LLMs and Graph Neural Nets!

📢 Excited to release PyG (PyTorch Geometric) v2.5, including distributed training, a dedicated graph tensor representation, RecSys support, PyTorch 2.2 and native compilation support 🎉 Release Notes 👇 github.com/pyg-team/pytor… 🧵 A thread [1/6]

Making tabular machine learning easy with PyToch Frame. Check it out!

Super excited about our new open-source library, PyTorch Frame, that we've been working on at @pyg_team @kumo_ai_team 🕷️☁️ It's built on top of @pytorch, and it works nicely with other open-source libraries like PyG and @huggingface transformers🤗 Check out examples here:…

🚀🎉 Excited to announce 🌟 PyTorch Frame 🌟 - our new open-source initiative in PyTorch! Dive into multi-modal tabular deep learning like never before! Link: github.com/pyg-team/pytor… #PyTorch #OpenSource (1/6)