Geometric Embedding Alignment via Curvature Matching in Transfer Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914522366738432 |
|---|---|
| author | Ko, Sung Moon Lee, Jaewan Lee, Sumin Yim, Soorin Bae, Kyunghoon Han, Sehui |
| author_facet | Ko, Sung Moon Lee, Jaewan Lee, Sumin Yim, Soorin Bae, Kyunghoon Han, Sehui |
| contents | 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 sourced from various domains and demonstrate significant performance gains over existing benchmark model under both random (14.4%) and scaffold (8.3%) data splits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13015 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Geometric Embedding Alignment via Curvature Matching in Transfer Learning Ko, Sung Moon Lee, Jaewan Lee, Sumin Yim, Soorin Bae, Kyunghoon Han, Sehui Machine Learning Artificial Intelligence 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 sourced from various domains and demonstrate significant performance gains over existing benchmark model under both random (14.4%) and scaffold (8.3%) data splits. |
| title | Geometric Embedding Alignment via Curvature Matching in Transfer Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.13015 |