[2510.01634] CAT: Curvature-Adaptive Transformers for Geometry-Aware Learning

Abstract:Transformers achieve strong performance across diverse domains but implicitly assume Euclidean geometry in their attention mechanisms, limiting their effectiveness on data with non-Euclidean structure. While recent extensions to hyperbolic and spherical spaces show promise for hierarchical and cyclical patterns, respectively, they require committing to a single geometry a priori, reducing flexibility when data exhibits mixed geometric properties. We introduce the Curvature-Adaptive Transformer (CAT), a novel architecture that dynamically learns per-token routing across three geometric attention branches through a lightweight, differentiable gating mechanism. Unlike fixed-geometry approaches, CAT enables adaptive geometric specialization, routing tokens to the appropriate curvature based on their local relational structure. The routing network provides interpretable curvature preferences while each branch employs geometry-specific operations optimized for its respective manifold. On knowledge graph completion benchmarks (FB15k-237, WN18RR), CAT achieves approximately 10% improvements in MRR and Hits@10 over fixed-geometry baselines with minimal overhead (5% parameter increase, comparable inference time). These results demonstrate that learned geometric adaptation outperforms any single fixed geometry for complex relational reasoning, establishing CAT as a scalable and interpretable foundation for mixture-of-geometry architectures across language, vision, and multimodal domains.

# link_11fm4m5v5ed.pdf ## Metadata - PDFFormatVersion=1.7 - IsLinearized=false - IsAcroFormPresent=false - IsXFAPresent=false - IsCollectionPresent=false - IsSignaturesPresent=false - Author=Ryan Y. Lin; Siddhartha Ojha; Nicholas Bai - Creator=arXiv GenPDF (tex2pdf:) - Custom.DOI=https://doi.org/10.48550/arXiv.2510.01634 - Custom.License=http://creativecommons.org/licenses/by/4.0/ - Custom.PTEX.Fullbanner=This is pdfTeX, Version 3.141592653-2.6-1.40.28 (TeX Live 2025) kpathsea version 6.4.1 - Custom.arXivID=https://arxiv.org/abs/2510.01634v1 - Producer=pikepdf 8.15.1 - Title=CAT: Curvature-Ada

saved by

• Vihan Tiwari

related reading

• A Mathematical Framework for Transformer Circuitstransformer-circuits.pub
• transformer_attention.pdfarxiv.org
• Transformers from Scratche2eml.school
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• The Annotated Transformernlp.seas.harvard.edu
• [1706.03762] Attention Is All You Needarxiv.org
• The Annotated Transformernlp.seas.harvard.edu
• 1706.03762arxiv.org
• [2207.02505] Pure Transformers are Powerful Graph Learnersarxiv.org
• [2512.19428] Attention Is Not What You Needarxiv.org
• The Transformer Family Version 2.0 | Lil'Loglilianweng.github.io
• Transformer (deep learning) - Wikipediaen.wikipedia.org