K3-Node launches: a Keras 3-native GNN library with 100% PyG API parity across JAX, torch and TF
fchollet · x · 2026-09-29
François Chollet shared K3-Node, an open-source graph neural network library built natively on Keras 3.
- Multi-backend: write GNN models once and run on TensorFlow, PyTorch, or JAX with full acceleration on NVIDIA GPUs, Apple Silicon, and TPUs
- API parity: claims 100% public API compatibility with PyTorch Geometric (PyG) for easy migration
- Incorporates state-of-the-art foundation models and architectures from Spektral and StellarGraph
- Open-sourced on GitHub with docs and a porting checklist
More from Research
- AI agents claim Collatz breakthrough: positive proportion of numbers reach 1, Lean-formalized — AlexKontorovich · 2026-09-29
- Averaging OCR attention heads across layers accidentally yields a strong interpretability lens — benno_krojer · 2026-09-29
- Self-supervised multisensory pretraining robot RL paper wins best student paper at IROS — GeorgiaChal · 2026-09-29
- saezlab open-sources mc-ASTRA, a Python framework for studying tissue remodeling across patients and perturbations — anshulkundaje · 2026-09-29
- Sampling the SK Model at β<1: New Polynomial-Time Algorithm Closes a 2022 Open Problem — canondetortugas · 2026-09-29
- Testing Jev on Reasoning-Intensive Regression: Wicked Fast but Classification-Focused — dbreunig · 2026-09-29