Geometric Embedding Alignment via Curvature Matching in Transfer Learning

ICLR 2026 Conference Submission15114 Authors

Keywords: Geometrical Deeplearning, Transfer Learning, Molecular Property Prediction

TL;DR: A novel transfer learning algorithm leverages Riemannian differential geometry, boosting performance by aligning latent representations across tasks through Ricci scalar curvature matching.

Abstract: Geometrical interpretations of deep learning models offer insightful perspectives into their underlying mathematical structures. In this work, we introduce a novel approach that leverages differential geometry, particularly concepts from Riemannian geometry, to integrate multiple models into a unified transfer learning framework. By aligning the Ricci curvature of latent space of individual models, we construct an interrelated architecture, namely Geometric Embedding Alignment via cuRvature matching in transfer learning (GEAR), which ensures comprehensive geometric representation across datapoints. This framework enables the effective aggregation of knowledge from diverse sources, thereby improving performance on target tasks. We evaluate our model on 23 molecular task pairs and demonstrate significant performance gains over existing benchmark models—achieving improvements of at least 14.4% under random splits and 8.3% under scaffold splits.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 15114