GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory

• URL: http://arxiv.org/abs/2406.12375v1
• Date: Tue, 18 Jun 2024 08:03:51 GMT
• Title: GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory
• Authors: Haoze Wu, Zihan Qiu, Zili Wang, Hang Zhao, Jie Fu,
• Abstract summary: Mixture-of-Experts (MoE) has been demonstrated as an efficient method to scale up models. We propose a new fine-tuning method, GW-MoE, to address this issue.
• Score: 49.536752342048075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixture-of-Experts (MoE) has been demonstrated as an efficient method to scale up models. By dynamically and sparsely selecting activated experts, MoE can effectively reduce computational costs. Despite the success, we observe that many tokens in the MoE models have uncertain routing results. These tokens have nearly equal scores for choosing each expert, and we demonstrate that this uncertainty can lead to incorrect selections. Inspired by the Global Workspace Theory (GWT), we propose a new fine-tuning method, GW-MoE, to address this issue. The core idea is to broadcast the uncertain tokens across experts during fine-tuning. Therefore, these tokens can acquire the necessary knowledge from any expert during inference and become less sensitive to the choice. GW-MoE does not introduce additional inference overhead. We validate that GW can mitigate the uncertain problem and consistently improve in different tasks (text classification, question answering, summarization, code generation, and mathematical problem solving) and model sizes (650M and 8B parameters).

Related papers

• Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model [20.979790612689992]
  Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs) Existing MoE methods in LVLMs encourage different experts to handle different tokens, and they usually employ a router to predict the routing of each token. This paper proposes a novel method based on token-level gradient analysis, i.e., Solving Token Gradient Conflict (STGC)
  arXiv  Detail & Related papers  (2024-06-28T13:20:17Z)
• A Closer Look into Mixture-of-Experts in Large Language Models [26.503570706063634]
  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.
  arXiv  Detail & Related papers  (2024-06-26T10:07:57Z)
• AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models [14.646419975663367]
  We introduce AdaMoE to realize token-adaptive routing for MoE. AdaMoE does not force each token to occupy a fixed number of null experts. It can reduce average expert load (FLOPs) while achieving superior performance.
  arXiv  Detail & Related papers  (2024-06-19T05:47:10Z)
• 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)
• Toward Inference-optimal Mixture-of-Expert Large Language Models [55.96674056805708]
  We study the scaling law of MoE-based large language models (LLMs) We find that MoEs with a few (4/8) experts are the most serving efficient solution under the same performance, but costs 2.5-3.5x more in training. We propose to amend the scaling law of MoE by introducing inference efficiency as another metric besides the validation loss.
  arXiv  Detail & Related papers  (2024-04-03T16:33:42Z)
• 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)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts [64.94129594112557]
  Merging Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. We propose to merge most of the parameters while upscaling the Transformer layers to a weight-ensembling mixture of experts (MoE) module.
  arXiv  Detail & Related papers  (2024-02-01T08:58:57Z)
• Training Chain-of-Thought via Latent-Variable Inference [30.21067593018967]
  Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a chain-of-thought'' prompt. Naively combining CoT with supervised tuning requires supervision not just of the correct answers, but also of detailed rationales that lead to those answers. We propose a fine-tuning strategy that tries to maximize the emphmarginal log-likelihood of generating a correct answer using CoT prompting.
  arXiv  Detail & Related papers  (2023-11-28T17:47:32Z)
• 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.