paper-with-me

홈 › Papers

Rotary Position Encodings for Graphs

2025-09-26 · Isaac Reid, Arijit Sehanobish, Cederik Höfs, Bruno Mlodozeniec, Leonhard Vulpius, Federico Barbero, Adrian Weller, Krzysztof Choromanski, Richard E. Turner, Petar Veličković arxiv

We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find that rotating tokens depending on the spectrum of the graph Laplacian efficiently injects structural information into the attention mechanism, boosting performance in synthetic and real-world graph learning tasks. This approach, coined _Wave-Induced Rotary Encodings_ (WIRE), enjoys intriguing theoretical properties: it recovers regular RoPE on grids, and depends asymptotically on the graph effective resistance. Unlike bias-based relative position encodings, WIRE is compatible with linear attention.

📄 PDF Abstract BibTeX arXiv:2509.22259

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

Rotary Outliers and Rotary Offset Features in Large Language Models

2025-03-03 · André Jonasson

Transformer-based Large Language Models (LLMs) rely on positional encodings to provide sequence position information to their attention mechanism. Rotary Positional Encodings (RoPE), which encode relative position by rot…

Position

LieRE: Generalizing Rotary Position Encodings

2024-06-14 · Sophie Ostmeier, Brian Axelrod, Michael E. Moseley, Akshay Chaudhari 외

While Rotary Position Embeddings (RoPE) for large language models have become widely adopted, their application for other modalities has been slower. Here, we introduce Lie group Relative position Encodings (LieRE) that …

image-classificationImage ClassificationPosition

Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity

2026-06-16 · Viet-Hoang Tran, Vinh Khanh Bui, Van-Hoan Trinh, Tan Lai Ngoc 외 arxiv

Neural network parameter spaces are inherently non-injective, as distinct parameter configurations can realize identical functions through functional equivalence. While this symmetry is well understood in classical fully…

Round and Round We Go! What makes Rotary Positional Encodings useful?

2024-10-08 · Federico Barbero, Alex Vitvitskyi, Christos Perivolaropoulos, Razvan Pascanu 외

Positional Encodings (PEs) are a critical component of Transformer-based Large Language Models (LLMs), providing the attention mechanism with important sequence-position information. One of the most popular types of enco…

G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera Heterogeneity

2026-09-14 · Shuo Zhang, Xin Su, Wei Wang, Jun Liu 외 arxiv

We study relative position encoding for multi-view vision Transformers under camera heterogeneity, including varying fields of view (FoVs) or projection models. Existing rotary relative position encodings commonly use im…

3D Reconstruction