paper-with-me

홈 › Papers

Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers

2025-01-01 · CVPR 2025 1 · Yichen Xiao, Shuai Wang, Dehao Zhang, Wenjie Wei, Yimeng Shan, Xiaoli Liu, Yulin Jiang, Malu Zhang

Transformers significantly raise the performance limits across various tasks, spurring research into integrating them into spiking neural networks. However, a notable performance gap remains between existing spiking Transformers and their artificial neural network counterparts. Here, we first analyze the cause of this gap and attribute it to the dot product's ineffectiveness in measuring similarity between spiking queries and keys, due to numerous non-spiking events. To address this, we propose a novel a-XNOR similarity measure tailored for spike trains. It redefines the correlation between non-spike pairs as a specific value a, effectively overcoming the limitations of dot-product similarity. Furthermore, considering the sparse nature of spike trains where spikes carry more information than non-spikes, the a-XNOR similarity correspondingly highlights the distinct importance of spikes over non-spikes. Extensive experiments demonstrate that a-XNOR similarity significantly improves performance across different spiking Transformer architectures on various static and neuromorphic datasets, further revealing the potential of spiking Transformers.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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 $x$…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks

2024-03-21 · CVPR 2024 1 · Xinyu Shi, Zecheng Hao, Zhaofei Yu

The remarkable success of Vision Transformers in Artificial Neural Networks (ANNs) has led to a growing interest in incorporating the self-attention mechanism and transformer-based architecture into Spiking Neural Networ…

Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer

2025-02-28 · Yufei Guo, Xiaode Liu, Yuanpei Chen, Weihang Peng 외

Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming. Spiking Neural Networks have emerged as a promising ener…

Spiking Transformer: Introducing Accurate Addition-Only Spiking Self-Attention for Transformer

2025-01-01 · CVPR 2025 1 · Yufei Guo, Xiaode Liu, Yuanpei Chen, Weihang Peng 외

Transformers have demonstrated outstanding performance across a wide range of tasks, owing to their self-attention mechanism, but they are highly energy-consuming. Spiking Neural Networks have emerged as a promising …

Winner-Take-All Spiking Transformer for Language Modeling

2026-04-13 · Chenlin Zhou, Sihang Guo, Jiaqi Wang, Dongyang Ma 외 arxiv

Spiking Transformers, which combine the scalability of Transformers with the sparse, energy-efficient property of Spiking Neural Networks (SNNs), have achieved impressive results in neuromorphic and vision tasks and attr…

Natural Language Understanding

Spiking GATs: Learning Graph Attentions via Spiking Neural Network

2022-09-05 · Beibei Wang, Bo Jiang

Graph Attention Networks (GATs) have been intensively studied and widely used in graph data learning tasks. Existing GATs generally adopt the self-attention mechanism to conduct graph edge attention learning, requiring e…

Graph Attention