Sovereign 8s.is mirror of standardgalactic/PlatonicRep
  • Python 79.7%
  • Jupyter Notebook 20.3%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2026-03-09 16:24:20 +08:00
images Rebuilt the repo 2025-11-24 13:19:30 +08:00
mp-20 modification 2025-12-09 21:17:15 +08:00
.DS_Store modification 2025-12-09 21:17:15 +08:00
anchor_selection.py Updated extractor and selector 2025-12-18 11:01:46 +08:00
found_indices_spacegroup221new.csv Modified 2025-11-29 12:54:32 +08:00
LICENSE Initial commit 2025-11-13 14:10:26 +08:00
manifold_distance.py Update the manifold distance calculation code 2026-03-09 16:24:20 +08:00
mlip_embedding_extractor.py Updated extractor and selector 2025-12-18 11:01:46 +08:00
PlatonicRep.ipynb Update the manifold distance calculation code 2026-03-09 16:24:20 +08:00
README.md Update README.md 2025-11-26 18:12:39 +08:00

PlatonicRep

Platonic Representation

Platonic Representation of Foundation Machine Learning Interatomic Potentials

🔬 Overview

Foundation machine learning interatomic potentials (MLIPs) are trained on overlapping chemical spaces, yet their latent representations remain model-specific and incommensurable. This work introduces the Platonic representation—a unified framework that aligns embeddings from diverse MLIPs into a common geometric space.

Key Contributions:

🎯 Universal alignment framework: Projects 7+ MLIP models into shared latent space using anchor-based transformation 📊 Model interoperability: Enables direct cross-model comparison via optimal transport and similarity metrics 🔧 Practical applications: Zero-shot model stitching, fine-tuning diagnostics, and symmetry-breaking detection 🧪 Physical validation: Correlates geometric distortions with prediction failures (phonon dispersions, rotational invariance)

🚀 Quick Start

Construction flow

Open Notebook :)

  1. Load a foundation model
  2. Extract embeddings from structures
  3. Initialize Platonic transform with K=100 anchors
  4. Transform to unified space
  5. Compare models
  6. Compute similarity

📊 Reproducing Paper Results

Download Pre-extracted Embeddings

Zenodo (DOI: 10.5281/zenodo.17721681)

Packages needed

🧮 Already convergence-tested Models

Model Architecture Training Data Status
MACE-MP-0-large E(3)-equiv. GNN MPtrj ✅ Supported
MACE-MP-0-medium E(3)-equiv. GNN MPtrj ✅ Supported
MACE-MP-0-small E(3)-equiv. GNN MPtrj ✅ Supported
MACE-OMat E(3)-equiv. GNN OMat24 ✅ Supported
SevenNet-OMat E(3)-equiv. GNN OMat24 ✅ Supported
Orb-v3-conservative GNN OMat24 ✅ Supported
Orb-v3-direct GNN OMat24 ✅ Supported
NequIP-OAM-L E(3)-equiv. GNN OMat24, Alexandria, MPtrj ✅ Supported
NequIP-MP-L E(3)-equiv. GNN OMat24, Alexandria, MPtrj ✅ Supported
MACE-MPA-0 E(3)-equiv. GNN MPTrj + sAlex ✅ Supported

Made with ❤️ by the Walsh Materials Design Group

🗺️ Roadmap v1.0 (Current): Core framework + paper reproduction Contributions toward these goals are welcome!

Last Updated: January 2025