MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition

• URL: http://arxiv.org/abs/2411.01016v1
• Date: Fri, 01 Nov 2024 20:37:58 GMT
• Title: MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
• Authors: Cheng Yang, Yang Sui, Jinqi Xiao, Lingyi Huang, Yu Gong, Yuanlin Duan, Wenqi Jia, Miao Yin, Yu Cheng, Bo Yuan,
• Abstract summary: We introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. Experiments on Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite, and Mixtral-8$times$7B demonstrate that our proposed methods can both reduce the model size and enhance inference efficiency.
• Score: 32.97035551579975
• License:
• Abstract: The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with considerably fewer activated parameters. Despite this efficiency, their enormous parameter size still leads to high deployment costs. In this paper, we introduce a two-stage compression method tailored for MoE to reduce the model size and decrease the computational cost. First, in the inter-expert pruning stage, we analyze the importance of each layer and propose the Layer-wise Genetic Search and Block-wise KT-Reception Field with the non-uniform pruning ratio to prune the individual expert. Second, in the intra-expert decomposition stage, we apply the low-rank decomposition to further compress the parameters within the remaining experts. Extensive experiments on Qwen1.5-MoE-A2.7B, DeepSeek-V2-Lite, and Mixtral-8$\times$7B demonstrate that our proposed methods can both reduce the model size and enhance inference efficiency while maintaining performance in various zero-shot tasks. The code will be available at \url{https://github.com/xiaochengsky/MoEI-2.git}

Related papers

• Mixture of A Million Experts [1.240096657086732]
  This paper introduces PEER, a novel layer design that utilizes the product key technique for sparse retrieval from a vast pool of experts. Experiments on language modeling tasks demonstrate that PEER layers outperform dense FFWs and coarse-grained MoEs in terms of performance-compute trade-off.
  arXiv  Detail & Related papers  (2024-07-04T20:59:20Z)
• Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging [14.123313596780726]
  We propose Manifold-Based Knowledge Alignment and Layer Merging Compression (MKA) MKA uses manifold learning and the Normalized Pairwise Information Bottleneck measure to merge similar layers, reducing model size while preserving essential performance. Our findings show that MKA not only preserves model performance but also achieves substantial compression ratios, outperforming traditional pruning methods.
  arXiv  Detail & Related papers  (2024-06-24T05:57:55Z)
• 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)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models [53.638791265113625]
  Sparsity-Preserved efficient fine-tuning method for large language models. Code will be made available at https://github.com/Lucky-Lance/SPP.
  arXiv  Detail & Related papers  (2024-05-25T04:55:27Z)
• Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization [40.15915011575071]
  Low-rank compression is a promising technique to reduce non-essential parameters in large language models. We conduct empirical research on the low-rank characteristics of large models. We propose a low-rank compression method suitable for large language models.
  arXiv  Detail & Related papers  (2024-05-17T08:27:12Z)
• SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts [49.01990048827639]
  We introduce SEER-MoE, a framework for reducing both the memory footprint and compute requirements of pre-trained MoE models. The first stage involves pruning the total number of experts using a heavy-hitters counting guidance, while the second stage employs a regularization-based fine-tuning strategy to recover accuracy loss. Our empirical studies demonstrate the effectiveness of our method, resulting in a sparse MoEs model optimized for inference efficiency with minimal accuracy trade-offs.
  arXiv  Detail & Related papers  (2024-04-07T22:13:43Z)
• Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models [90.14693869269519]
  MoE LLMs can achieve higher performance with fewer parameters, but it is still hard to deploy them due to their immense parameter sizes. This paper mainly aims to enhance the deployment efficiency of MoE LLMs by introducing plug-and-play expert-level sparsification techniques.
  arXiv  Detail & Related papers  (2024-02-22T18:56:07Z)
• Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity [88.62935593360162]
  Large Language Models (LLMs) are renowned for their remarkable performance across diverse domains. We introduce a novel LLM pruning methodology that incorporates a tailored set of non-uniform layerwise sparsity ratios, termed as Outlier Weighed Layerwise sparsity (OWL) OWL exhibits a remarkable performance gain, surpassing the state-of-the-art Wanda and SparseGPT by 61.22 and 6.80 perplexity at a high sparsity level of 70%, respectively.
  arXiv  Detail & Related papers  (2023-10-08T14:22:58Z)

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.