paper-with-me

홈 › Papers

SparseSpikformer: A Co-Design Framework for Token and Weight Pruning in Spiking Transformer

2023-11-15 · Yue Liu, Shanlin Xiao, Bo Li, Zhiyi Yu

As the third-generation neural network, the Spiking Neural Network (SNN) has the advantages of low power consumption and high energy efficiency, making it suitable for implementation on edge devices. More recently, the most advanced SNN, Spikformer, combines the self-attention module from Transformer with SNN to achieve remarkable performance. However, it adopts larger channel dimensions in MLP layers, leading to an increased number of redundant model parameters. To effectively decrease the computational complexity and weight parameters of the model, we explore the Lottery Ticket Hypothesis (LTH) and discover a very sparse ($\ge$90%) subnetwork that achieves comparable performance to the original network. Furthermore, we also design a lightweight token selector module, which can remove unimportant background information from images based on the average spike firing rate of neurons, selecting only essential foreground image tokens to participate in attention calculation. Based on that, we present SparseSpikformer, a co-design framework aimed at achieving sparsity in Spikformer through token and weight pruning techniques. Experimental results demonstrate that our framework can significantly reduce 90% model parameters and cut down Giga Floating-Point Operations (GFLOPs) by 20% while maintaining the accuracy of the original model.

📄 PDF Abstract BibTeX arXiv:2311.08806

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 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 $x$…
Position-Wise Feed-Forward Layer 설명 없음
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…
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…

Similar Papers 제목 키워드 기반

Accelerating ViT Inference on FPGA through Static and Dynamic Pruning

2024-03-21 · Dhruv Parikh, Shouyi Li, Bingyi Zhang, Rajgopal Kannan 외

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight a…

Leveraging KV Similarity for Online Structured Pruning in LLMs

2025-12-08 · Jungmin Lee, Gwangeun Byeon, Yulhwa Kim, Seokin Hong arxiv

Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not general…

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models

2026-04-01 · Dong-Jae Lee, Sunghyun Baek, Junmo Kim arxiv

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate th…

Saliency-driven Dynamic Token Pruning for Large Language Models

2025-04-06 · Yao Tao, Yehui Tang, Yun Wang, Mingjian Zhu 외

Despite the recent success of large language models (LLMs), LLMs are particularly challenging in long-sequence inference scenarios due to the quadratic computational complexity of the attention mechanism. Inspired by the…

Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

2025-09-28 · Shaobo Wang, Jiaming Wang, Jiajun Zhang, Cong Wang 외 arxiv

As supervised fine-tuning (SFT) evolves from a lightweight post-training step into a compute-intensive phase rivaling mid-training in scale, data efficiency has become critical for aligning large language models (LLMs) u…