Saved in:
Bibliographic Details
Main Authors: Qu, Cheng Kevin, Ly, Andrew, Gong, Pulin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909900589760512
author Qu, Cheng Kevin
Ly, Andrew
Gong, Pulin
author_facet Qu, Cheng Kevin
Ly, Andrew
Gong, Pulin
contents Attention mechanisms underpin the computational power of Transformer models, which have achieved remarkable success across diverse domains. Yet understanding and extending the principles underlying self-attention remains a key challenge for advancing artificial intelligence. Drawing inspiration from the multiscale dynamics of biological attention and from dynamical systems theory, we introduce Fractional Neural Attention (FNA), a principled, neuroscience-inspired framework for multiscale information processing. FNA models token interactions through Lévy diffusion governed by the fractional Laplacian, intrinsically realizing simultaneous short- and long-range dependencies across multiple scales. This mechanism yields greater expressivity and faster information mixing, advancing the foundational capacity of Transformers. Theoretically, we show that FNA's dynamics are governed by the fractional diffusion equation, and that the resulting attention networks exhibit larger spectral gaps and shorter path lengths -- mechanistic signatures of enhanced computational efficiency. Empirically, FNA achieves competitive text-classification performance even with a single layer and a single head; it also improves performance in image processing and neural machine translation. Finally, the diffusion map algorithm from geometric harmonics enables dimensionality reduction of FNA weights while preserving the intrinsic structure of embeddings and hidden states. Together, these results establish FNA as a principled mechanism connecting self-attention, stochastic dynamics, and geometry, providing an interpretable, biologically grounded foundation for powerful, neuroscience-inspired AI.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fractional neural attention for efficient multiscale sequence processing
Qu, Cheng Kevin
Ly, Andrew
Gong, Pulin
Machine Learning
Artificial Intelligence
Dynamical Systems
Probability
Biological Physics
Attention mechanisms underpin the computational power of Transformer models, which have achieved remarkable success across diverse domains. Yet understanding and extending the principles underlying self-attention remains a key challenge for advancing artificial intelligence. Drawing inspiration from the multiscale dynamics of biological attention and from dynamical systems theory, we introduce Fractional Neural Attention (FNA), a principled, neuroscience-inspired framework for multiscale information processing. FNA models token interactions through Lévy diffusion governed by the fractional Laplacian, intrinsically realizing simultaneous short- and long-range dependencies across multiple scales. This mechanism yields greater expressivity and faster information mixing, advancing the foundational capacity of Transformers. Theoretically, we show that FNA's dynamics are governed by the fractional diffusion equation, and that the resulting attention networks exhibit larger spectral gaps and shorter path lengths -- mechanistic signatures of enhanced computational efficiency. Empirically, FNA achieves competitive text-classification performance even with a single layer and a single head; it also improves performance in image processing and neural machine translation. Finally, the diffusion map algorithm from geometric harmonics enables dimensionality reduction of FNA weights while preserving the intrinsic structure of embeddings and hidden states. Together, these results establish FNA as a principled mechanism connecting self-attention, stochastic dynamics, and geometry, providing an interpretable, biologically grounded foundation for powerful, neuroscience-inspired AI.
title Fractional neural attention for efficient multiscale sequence processing
topic Machine Learning
Artificial Intelligence
Dynamical Systems
Probability
Biological Physics
url https://arxiv.org/abs/2511.10208