Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion

• URL: http://arxiv.org/abs/2310.04361v3
• Date: Fri, 7 Jun 2024 13:03:34 GMT
• Title: Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
• Authors: Filip Szatkowski, Bartosz Wójcik, Mikołaj Piórczyński, Simone Scardapane,
• Abstract summary: Transformer models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost. We show that the efficiency of the conversion can be significantly enhanced by a proper regularization of the activation sparsity of the base model. We also introduce a more effective dynamic-k expert selection rule that adjusts the number of executed experts on a per-token basis.
• Score: 4.716845031095804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost by converting parts of the network into equivalent Mixture-of-Experts (MoE) layers. Despite the crucial role played by activation sparsity, its impact on this process remains unexplored. In particular, we show that the efficiency of the conversion can be significantly enhanced by a proper regularization of the activation sparsity of the base model. Moreover, motivated by the high variance of the number of activated neurons for different inputs, we introduce a more effective dynamic-k expert selection rule that adjusts the number of executed experts on a per-token basis. Finally, we extend this approach to multi-head attention projections, which results in additional savings compared to only converting the FFN blocks. The proposed method, Dense to Dynamic-$k$ Mixture-of-Experts (D2DMoE), outperforms existing approaches on common NLP and vision tasks, allowing us to save up to 60% of inference cost without significantly affecting model performance.

Related papers

• MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More [71.0473038084673]
  We propose MC-MoE, a training-free Mixture-Compressor for Mixture-of-Experts large language models (MoE-LLMs) MC-MoE leverages the significance of both experts and tokens to achieve an extreme compression. For instance, at 2.54 bits, MC-MoE compresses 76.6% of the model, with only a 3.8% average accuracy loss.
  arXiv  Detail & Related papers  (2024-10-08T18:09:38Z)
• CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification [7.8430836312711465]
  Large language models (LLMs) on edge devices present significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these challenges by reducing the number of activated neurons during inference. This paper introduces CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification.
  arXiv  Detail & Related papers  (2024-09-02T16:41:44Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights [2.8461446020965435]
  We introduce LD-Pruner, a novel performance-preserving structured pruning method for compressing Latent Diffusion Models. We demonstrate the effectiveness of our approach on three different tasks: text-to-image (T2I) generation, Unconditional Image Generation (UIG) and Unconditional Audio Generation (UAG)
  arXiv  Detail & Related papers  (2024-04-18T06:35:37Z)
• Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning [50.73666458313015]
  Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications. MoE has been emerged as a promising solution with its sparse architecture for effective task decoupling. Intuition-MoR1E achieves superior efficiency and 2.15% overall accuracy improvement across 14 public datasets.
  arXiv  Detail & Related papers  (2024-04-13T12:14:58Z)
• 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)
• FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization [5.182014186927254]
  Federated Learning (FL) has been successfully adopted for distributed training and inference of large-scale Deep Neural Networks (DNNs) We contribute with a novel FL framework (coined FedDIP) which combines (i) dynamic model pruning with error feedback to eliminate redundant information exchange. We provide convergence analysis of FedDIP and report on a comprehensive performance and comparative assessment against state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-13T08:51:19Z)
• Value function estimation using conditional diffusion models for control [62.27184818047923]
  We propose a simple algorithm called Diffused Value Function (DVF) It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model. We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
  arXiv  Detail & Related papers  (2023-06-09T18:40:55Z)
• Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity [37.04254056062765]
  Stratified Mixture of Experts (SMoE) models can assign dynamic capacity to different tokens. We show SMoE outperforms multiple state-of-the-art MoE models with the same or fewer parameters.
  arXiv  Detail & Related papers  (2023-05-03T15:18:18Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)

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.