A Closer Look into Mixture-of-Experts in Large Language Models

• URL: http://arxiv.org/abs/2406.18219v2
• Date: Sun, 20 Oct 2024 05:21:53 GMT
• Title: A Closer Look into Mixture-of-Experts in Large Language Models
• Authors: Ka Man Lo, Zeyu Huang, Zihan Qiu, Zili Wang, Jie Fu,
• Abstract summary: Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance. MoE architecture could increase the model size without sacrificing computational efficiency. We make an initial attempt to understand the inner workings of MoE-based large language models.
• Score: 26.503570706063634
• License:
• Abstract: Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance, especially for language tasks. By sparsely activating a subset of parameters for each token, MoE architecture could increase the model size without sacrificing computational efficiency, achieving a better trade-off between performance and training costs. However, the underlying mechanism of MoE still lacks further exploration, and its modularization degree remains questionable. In this paper, we make an initial attempt to understand the inner workings of MoE-based large language models. Concretely, we comprehensively study the parametric and behavioral features of three popular MoE-based models and reveal some intriguing observations, including 1) Neurons act like fine-grained experts; 2) The router of MoE usually selects experts with larger output norms; 3) The expert diversity increases as the layer increases, while the last layer is an outlier, which is further validated by an initial experiment. Based on the observations, we also provide suggestions for a broad spectrum of MoE practitioners, such as router design and expert allocation. We hope this work could shed light on future research on the MoE framework and other modular architectures. Code is available at https://github.com/kamanphoebe/Look-into-MoEs.

Related papers

• ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts [71.11994027685974]
  We integrate the MoE structure into the classic Vision Transformer (ViT), naming it ViMoE, and explore the potential of applying MoE to vision. We observe that the performance is sensitive to the configuration of MoE layers, making it challenging to obtain optimal results without careful design. To address this, we introduce a shared expert to learn and capture common information, serving as an effective way to construct stable ViMoE.
  arXiv  Detail & Related papers  (2024-10-21T07:51:17Z)
• 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)
• A Survey on Mixture of Experts [11.801185267119298]
  The mixture of experts (MoE) has emerged as an effective method for substantially scaling up model capacity with minimal overhead. MoE has emerged as an effective method for substantially scaling up model capacity with minimal overhead. This survey seeks to bridge that gap, serving as an essential resource for researchers delving into the intricacies of MoE.
  arXiv  Detail & Related papers  (2024-06-26T16:34:33Z)
• LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training [21.359073227913303]
  Training MoE from scratch in a large-scale setting still suffers from data-hungry and instability problems. Motivated by this limit, we investigate building MoE models from existing dense large language models. Our LLaMA-MoE models significantly outperform dense models that contain similar activation parameters.
  arXiv  Detail & Related papers  (2024-06-24T11:43:07Z)
• Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast [58.98411447739218]
  Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. We propose Self-Contrast Mixture-of-Experts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding.
  arXiv  Detail & Related papers  (2024-05-23T12:45:29Z)
• Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization [51.98792406392873]
  Mixture of Experts (MoE) provides a powerful way to decompose dense layers into smaller, modular computations. A major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. We propose the Multilinear Mixture of Experts ($mu$MoE) layer to address this, focusing on vision models.
  arXiv  Detail & Related papers  (2024-02-19T21:20:22Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Mixture of Attention Heads: Selecting Attention Heads Per Token [40.04159325505842]
  Mixture of Attention Heads (MoA) is a new architecture that combines multi-head attention with the MoE mechanism. MoA achieves stronger performance than the standard multi-head attention layer. MoA also automatically differentiates heads' utilities, providing a new perspective to discuss the model's interpretability.
  arXiv  Detail & Related papers  (2022-10-11T04:54:05Z)
• Task-Specific Expert Pruning for Sparse Mixture-of-Experts [105.20605021416276]
  Mixture-of-Experts (MoE) model is powerful for large-scale pre-training. MoE is hard to be deployed on cloud or mobile environment. We propose a general method to progressively drop the non-professional experts for the target downstream task.
  arXiv  Detail & Related papers  (2022-06-01T07:09:01Z)

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.