High-Layer Attention Pruning with Rescaling

• URL: http://arxiv.org/abs/2507.01900v1
• Date: Wed, 02 Jul 2025 17:15:05 GMT
• Title: High-Layer Attention Pruning with Rescaling
• Authors: Songtao Liu, Peng Liu,
• Abstract summary: Pruning is a highly effective approach for compressing large language models (LLMs)<n>We propose a novel pruning algorithm that strategically prunes attention heads in the model's higher layers.<n>We conduct comprehensive experiments on a wide range of LLMs, including LLaMA3.1-8B, Mistral-7B-v0.3, Qwen2-7B, and Gemma2-9B.
• Score: 14.141903038286362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that indiscriminately removes some attention heads across all pruning layers, without considering their positions within the network architecture. In this work, we propose a novel pruning algorithm that strategically prunes attention heads in the model's higher layers. Since the removal of attention heads can alter the magnitude of token representations, we introduce an adaptive rescaling parameter that calibrates the representation scale post-pruning to counteract this effect. We conduct comprehensive experiments on a wide range of LLMs, including LLaMA3.1-8B, Mistral-7B-v0.3, Qwen2-7B, and Gemma2-9B. Our evaluation includes both generation and discriminative tasks across 27 datasets. The results consistently demonstrate that our method outperforms existing structured pruning methods. This improvement is particularly notable in generation tasks, where our approach significantly outperforms existing baselines.

Related papers

• Pruning Everything, Everywhere, All at Once [1.7811840395202343]
  Pruning structures in deep learning models efficiently reduces model complexity and improves computational efficiency.<n>We propose a new method capable of pruning different structures within a model as follows.<n>Iteratively repeating this process provides highly sparse models that preserve the original predictive ability.
  arXiv  Detail & Related papers  (2025-06-04T23:34:28Z)
• Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity [32.668409666483626]
  Existing pruning methods mainly focus on designing metrics to measure the importance of network components to guide pruning.<n>We propose an efficient method based on the trace of Fisher Information Matrix (FIM) to quantitatively measure and verify the different sensitivities across layers.<n>Based on this, we propose Mixed Sparsity Pruning (MSP) which uses a pruning-oriented evolutionary algorithm (EA) to determine the optimal sparsity levels for different layers.
  arXiv  Detail & Related papers  (2025-03-14T08:05:49Z)
• LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation [0.0]
  We propose a more accurate pruning metric based on the block-wise importance score propagation.<n>We evaluate the proposed method using LLaMA-7B, Vicuna-7B, and LLaMA-13B across common zero-shot tasks.
  arXiv  Detail & Related papers  (2024-12-09T11:57:16Z)
• Compressing Large Language Models with Automated Sub-Network Search [41.452512557226335]
  We consider model compression for Large Language Models to reduce model size while improving downstream task performance.<n>We phrase this as a neural architecture search problem that automatically prunes structural components.<n>Our method achieves upto 9.85% improvement on average on 11 diverse downstream tasks, while achieving up to 22% improvement of on-device latency.
  arXiv  Detail & Related papers  (2024-10-09T02:14:39Z)
• A deeper look at depth pruning of LLMs [49.30061112976263]
  Large Language Models (LLMs) are resource-intensive to train but more costly to deploy in production. Recent work has attempted to prune blocks of LLMs based on cheap proxies for estimating block importance. We show that adaptive metrics exhibit a trade-off in performance between tasks.
  arXiv  Detail & Related papers  (2024-07-23T08:40:27Z)
• Effective Layer Pruning Through Similarity Metric Perspective [0.0]
  Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Pruning structures from these models is a straightforward approach to reducing network complexity. Layer pruning often hurts the network predictive ability (i.e., accuracy) at high compression rates. This work introduces an effective layer-pruning strategy that meets all underlying properties pursued by pruning methods.
  arXiv  Detail & Related papers  (2024-05-27T11:54:51Z)
• Advancing Model Pruning via Bi-level Optimization [89.88761425199598]
  iterative magnitude pruning (IMP) is the predominant pruning method to successfully find 'winning tickets' One-shot pruning methods have been developed, but these schemes are usually unable to find winning tickets as good as IMP. We show that the proposed bi-level optimization-oriented pruning method (termed BiP) is a special class of BLO problems with a bi-linear problem structure.
  arXiv  Detail & Related papers  (2022-10-08T19:19:29Z)
• MLPruning: A Multilevel Structured Pruning Framework for Transformer-based Models [78.45898846056303]
  Pruning is an effective method to reduce the memory footprint and computational cost associated with large natural language processing models. We develop a novel MultiLevel structured Pruning framework, which uses three different levels of structured pruning: head pruning, row pruning, and block-wise sparse pruning.
  arXiv  Detail & Related papers  (2021-05-30T22:00:44Z)
• Neural Pruning via Growing Regularization [82.9322109208353]
  We extend regularization to tackle two central problems of pruning: pruning schedule and weight importance scoring. Specifically, we propose an L2 regularization variant with rising penalty factors and show it can bring significant accuracy gains. The proposed algorithms are easy to implement and scalable to large datasets and networks in both structured and unstructured pruning.
  arXiv  Detail & Related papers  (2020-12-16T20:16:28Z)
• Layer-adaptive sparsity for the Magnitude-based Pruning [88.37510230946478]
  We propose a novel importance score for global pruning, coined layer-adaptive magnitude-based pruning (LAMP) score. LAMP consistently outperforms popular existing schemes for layerwise sparsity selection.
  arXiv  Detail & Related papers  (2020-10-15T09:14:02Z)
• Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning [83.99191569112682]
  Magnitude-based pruning is one of the simplest methods for pruning neural networks. We develop a simple pruning method, coined lookahead pruning, by extending the single layer optimization to a multi-layer optimization. Our experimental results demonstrate that the proposed method consistently outperforms magnitude-based pruning on various networks.
  arXiv  Detail & Related papers  (2020-02-12T05:38:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.