A Sliding Layer Merging Method for Efficient Depth-Wise Pruning in LLMs

• URL: http://arxiv.org/abs/2502.19159v1
• Date: Wed, 26 Feb 2025 14:15:24 GMT
• Title: A Sliding Layer Merging Method for Efficient Depth-Wise Pruning in LLMs
• Authors: Xuan Ding, Yao Zhu, Yunjian Zhang, Chuanlong Xie,
• Abstract summary: This paper reveals the "Patch-like" feature relationship between layers in large language models by analyzing the correlation of the outputs of different layers in the reproducing kernel Hilbert space.<n>We propose a sliding layer merging method that dynamically selects and fuses consecutive layers from top to bottom according to a pre-defined similarity threshold.<n>Our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning.
• Score: 14.514670828712669
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compared to width-wise pruning, depth-wise pruning can significantly accelerate inference in resource-constrained scenarios. Howerver, treating the entire Transformer layer as the minimum pruning unit may degrade model performance by indiscriminately discarding the entire information of the layer. This paper reveals the "Patch-like" feature relationship between layers in large language models by analyzing the correlation of the outputs of different layers in the reproducing kernel Hilbert space. Building on this observation, we proposes a sliding layer merging method that dynamically selects and fuses consecutive layers from top to bottom according to a pre-defined similarity threshold, thereby simplifying the model structure while maintaining its performance. Extensive experiments on LLMs with various architectures and different parameter scales show that our method outperforms existing pruning techniques in both zero-shot inference performance and retraining recovery quality after pruning. In particular, in the experiment with 35\% pruning on the Vicuna-7B model, our method achieved a 1.654\% improvement in average performance on zero-shot tasks compared to the existing method. Moreover, we further reveal the potential of combining depth pruning with width pruning to enhance the pruning effect. Our codes are available at https://github.com/920927/SLM-a-sliding-layer-merging-method.

Related papers

• Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective [55.90119819642064]
  We address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective.<n>This refers to the cumulative effect of reconstruction errors throughout the sparsification process.<n>We derive a simple yet effective approach to layer-wise sparsity allocation that mitigates this issue.
  arXiv  Detail & Related papers  (2025-02-20T17:51:10Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy [19.14439554384161]
  This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs) By transitioning from constant to dynamic slicing, our method leverages the newly proposed Layer Redundancy (LR) score. Our findings show that our dynamic slicing approach not only maintains but, in many cases, enhances model performance compared to the baseline established by constant slicing methods.
  arXiv  Detail & Related papers  (2024-11-05T21:19:49Z)
• AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models [94.82766517752418]
  We propose AlphaPruning, which uses shape metrics to allocate layerwise sparsity ratios in a more theoretically principled manner. Our results show that AlphaPruning prunes LLaMA-7B to 80% sparsity while maintaining reasonable perplexity, marking a first in the literature on LLMs.
  arXiv  Detail & Related papers  (2024-10-14T03:35:11Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Streamlining Redundant Layers to Compress Large Language Models [21.27944103424621]
  This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs)<n>It is based on the observation that different layers have varying impacts on hidden states, enabling the identification of less important layers to be pruned.<n>Experiments show that LLM-Streamline outperforms both previous and concurrent state-of-the-art pruning methods in terms of both performance and training efficiency.
  arXiv  Detail & Related papers  (2024-03-28T04:12:13Z)
• The Unreasonable Ineffectiveness of the Deeper Layers [5.984361440126354]
  We study a simple layer-pruning strategy for popular families of open-weight pretrained LLMs. We find minimal degradation of performance until after a large fraction of the layers are removed. From a scientific perspective, the robustness of these LLMs to the deletion of layers implies either that current pretraining methods are not properly leveraging the parameters in the deeper layers of the network or that the shallow layers play a critical role in storing knowledge.
  arXiv  Detail & Related papers  (2024-03-26T17:20:04Z)
• ShortGPT: Layers in Large Language Models are More Redundant Than You Expect [38.148626520751385]
  We show that many layers of Large Language Models (LLMs) exhibit high similarity, and some layers play a negligible role in network functionality. We propose a straightforward pruning approach: layer removal, in which we directly delete the redundant layers. Experiments demonstrate that our method, which we call ShortGPT, significantly outperforms previous state-of-the-art (SOTA) methods in model pruning.
  arXiv  Detail & Related papers  (2024-03-06T17:04:18Z)
• LaCo: Large Language Model Pruning via Layer Collapse [56.92068213969036]
  Large language models (LLMs) based on transformer are witnessing a notable trend of size expansion. Existing methods such as model quantization, knowledge distillation, and model pruning are constrained by various issues. We propose a concise layer-wise structured pruner called textitLayer Collapse (LaCo), in which rear model layers collapse into a prior layer.
  arXiv  Detail & Related papers  (2024-02-17T04:16:30Z)
• Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency [31.572652956170252]
  Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.
  arXiv  Detail & Related papers  (2021-04-08T08:21:59Z)

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.