Leveraging Manifold Embeddings for Enhanced Graph Transformer Representations and Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908443101626368 |
|---|---|
| author | Jyothish, Ankit Jannesari, Ali |
| author_facet | Jyothish, Ankit Jannesari, Ali |
| contents | Graph transformers typically embed every node in a single Euclidean space, blurring heterogeneous topologies. We prepend a lightweight Riemannian mixture-of-experts layer that routes each node to various kinds of manifold, mixture of spherical, flat, hyperbolic - best matching its local structure. These projections provide intrinsic geometric explanations to the latent space. Inserted into a state-of-the-art ensemble graph transformer, this projector lifts accuracy by up to 3% on four node-classification benchmarks. The ensemble makes sure that both euclidean and non-euclidean features are captured. Explicit, geometry-aware projection thus sharpens predictive power while making graph representations more interpretable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07335 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Manifold Embeddings for Enhanced Graph Transformer Representations and Learning Jyothish, Ankit Jannesari, Ali Machine Learning Artificial Intelligence Graph transformers typically embed every node in a single Euclidean space, blurring heterogeneous topologies. We prepend a lightweight Riemannian mixture-of-experts layer that routes each node to various kinds of manifold, mixture of spherical, flat, hyperbolic - best matching its local structure. These projections provide intrinsic geometric explanations to the latent space. Inserted into a state-of-the-art ensemble graph transformer, this projector lifts accuracy by up to 3% on four node-classification benchmarks. The ensemble makes sure that both euclidean and non-euclidean features are captured. Explicit, geometry-aware projection thus sharpens predictive power while making graph representations more interpretable. |
| title | Leveraging Manifold Embeddings for Enhanced Graph Transformer Representations and Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.07335 |