Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts

• URL: http://arxiv.org/abs/2502.12928v1
• Date: Tue, 18 Feb 2025 15:09:58 GMT
• Title: Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts
• Authors: Leiyu Pan, Zhenpeng Su, Minxuan Lv, Yizhe Xiong, Xiangwen Zhang, Zijia Lin, Hui Chen, Jungong Han, Guiguang Ding, Cheng Luo, Di Zhang, Kun Gai, Deyi Xiong,
• Abstract summary: Finedeep is a deep-layered fine-grained expert architecture for dense models. Our framework partitions the feed-forward neural network layers of traditional dense models into small experts. A novel routing mechanism is proposed to determine each expert's contribution.
• Score: 82.74439280067492
• License:
• Abstract: Large language models have demonstrated exceptional performance across a wide range of tasks. However, dense models usually suffer from sparse activation, where many activation values tend towards zero (i.e., being inactivated). We argue that this could restrict the efficient exploration of model representation space. To mitigate this issue, we propose Finedeep, a deep-layered fine-grained expert architecture for dense models. Our framework partitions the feed-forward neural network layers of traditional dense models into small experts, arranges them across multiple sub-layers. A novel routing mechanism is proposed to determine each expert's contribution. We conduct extensive experiments across various model sizes, demonstrating that our approach significantly outperforms traditional dense architectures in terms of perplexity and benchmark performance while maintaining a comparable number of parameters and floating-point operations. Moreover, we find that Finedeep achieves optimal results when balancing depth and width, specifically by adjusting the number of expert sub-layers and the number of experts per sub-layer. Empirical results confirm that Finedeep effectively alleviates sparse activation and efficiently utilizes representation capacity in dense models.

Related papers

• Deep Discrete Encoders: Identifiable Deep Generative Models for Rich Data with Discrete Latent Layers [13.545948734057268]
  We propose an interpretable deep generative modeling framework for rich data types with discrete latent layers. We apply DDEs to three diverse real datasets for hierarchical topic modeling, image representation learning, response time modeling in educational testing, and obtain interpretable findings.
  arXiv  Detail & Related papers  (2025-01-02T18:56:23Z)
• Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts [75.85448576746373]
  We propose a method of grouping and pruning similar experts to improve the model's parameter efficiency. We validate the effectiveness of our method by pruning three state-of-the-art MoE architectures. The evaluation shows that our method outperforms other model pruning methods on a range of natural language tasks.
  arXiv  Detail & Related papers  (2024-07-12T17:25:02Z)
• 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)
• Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers [2.1165011830664673]
  Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks. The sheer size of these models poses challenges in terms of storage, training and inference due to the inclusion of billions of parameters through layer stacking. We show that even with fewer layers, LLMs maintain similar or better performance levels, particularly in prompt-based fine-tuning for text classification tasks.
  arXiv  Detail & Related papers  (2024-02-18T20:47:10Z)
• On Least Square Estimation in Softmax Gating Mixture of Experts [78.3687645289918]
  We investigate the performance of the least squares estimators (LSE) under a deterministic MoE model. We establish a condition called strong identifiability to characterize the convergence behavior of various types of expert functions. Our findings have important practical implications for expert selection.
  arXiv  Detail & Related papers  (2024-02-05T12:31:18Z)
• Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion [86.6191592951269]
  Merging models fine-tuned from common extensively pretrained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multitask model that performs well across diverse tasks. We propose the CONtinuous relaxation dis (Concrete) subspace learning method to identify a common lowdimensional subspace and utilize its shared information track interference problem without sacrificing performance.
  arXiv  Detail & Related papers  (2023-12-11T07:24:54Z)
• DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors [17.664439455504592]
  We propose a unified architecture, DeepPointMap, achieving excellent preference on both aspects. We utilize neural network to extract highly representative and sparse neural descriptors from point clouds. We showcase the versatility of our framework by extending it to more challenging multi-agent collaborative SLAM.
  arXiv  Detail & Related papers  (2023-12-05T11:40:41Z)
• Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts [74.40198929049959]
  Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to mix many multimodal low rank experts.
  arXiv  Detail & Related papers  (2023-12-01T23:04:27Z)
• MoEC: Mixture of Expert Clusters [93.63738535295866]
  Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation.
  arXiv  Detail & Related papers  (2022-07-19T06:09:55Z)
• Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability [3.021134753248103]
  Sparsely-gated Mixture of Expert (MoE) layers have been successfully applied for scaling large transformers. In this work, we apply sparse MoE layers to CNNs for computer vision tasks and analyze the resulting effect on model interpretability.
  arXiv  Detail & Related papers  (2022-04-22T09:40:23Z)

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.