paper-with-me

Papers

GridPE: Unifying Positional Encoding in Transformers with a Grid Cell-Inspired Framework

2024-06-11 · Boyang Li, Yulin Wu, Nuoxian Huang, Wenjia Zhang

Understanding spatial location and relationships is a fundamental capability for modern artificial intelligence systems. Insights from human spatial cognition provide valuable guidance in this domain. Neuroscientific discoveries have highlighted the role of grid cells as a fundamental neural component for spatial representation, including distance computation, path integration, and scale discernment. In this paper, we introduce a novel positional encoding scheme inspired by Fourier analysis and the latest findings in computational neuroscience regarding grid cells. Assuming that grid cells encode spatial position through a summation of Fourier basis functions, we demonstrate the translational invariance of the grid representation during inner product calculations. Additionally, we derive an optimal grid scale ratio for multi-dimensional Euclidean spaces based on principles of biological efficiency. Utilizing these computational principles, we have developed a Grid-cell inspired Positional Encoding technique, termed GridPE, for encoding locations within high-dimensional spaces. We integrated GridPE into the Pyramid Vision Transformer architecture. Our theoretical analysis shows that GridPE provides a unifying framework for positional encoding in arbitrary high-dimensional spaces. Experimental results demonstrate that GridPE significantly enhances the performance of transformers, underscoring the importance of incorporating neuroscientific insights into the design of artificial intelligence systems.

📄 PDF Abstract BibTeX arXiv:2406.07049

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

2024-02-13 · Guy Bar-Shalom, Beatrice Bevilacqua, Haggai Maron

In the realm of Graph Neural Networks (GNNs), two exciting research directions have recently emerged: Subgraph GNNs and Graph Transformers. In this paper, we propose an architecture that integrates both approaches, dubbe…

Weierstrass Positional Encoding for Vision Transformers

2026-05-20 · Zhihang Xin, Rui Wang, Xitong Hu, Xiaojun Wu arxiv

Vision Transformers have achieved remarkable success in computer vision, but their common use of learnable one-dimensional positional encodings weakens the inherent two-dimensional spatial structure of images after patch…

Comparing Graph Transformers via Positional Encodings

2024-02-22 · Mitchell Black, Zhengchao Wan, Gal Mishne, Amir Nayyeri 외

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of position…

Navigate

Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding

2024-10-16 · Daichi Hayakawa, Issei Sato

In this study, we provide constructive proof that Transformers can recognize and generate hierarchical language efficiently with respect to model size, even without the need for a specific positional encoding. Specifical…

Linearized Relative Positional Encoding

2023-07-18 · Zhen Qin, Weixuan Sun, Kaiyue Lu, Hui Deng 외

Relative positional encoding is widely used in vanilla and linear transformers to represent positional information. However, existing encoding methods of a vanilla transformer are not always directly applicable to a line…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+2