U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF

• URL: http://arxiv.org/abs/2404.16407v2
• Date: Thu, 8 Aug 2024 09:01:00 GMT
• Title: U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF
• Authors: Xingchen Song, Di Wu, Binbin Zhang, Dinghao Zhou, Zhendong Peng, Bo Dang, Fuping Pan, Chao Yang,
• Abstract summary: Mixture-of-Experts (MoE) have been proposed as an energy efficient path to larger and more capable language models. We benchmark our proposed model on a large scale inner-source dataset (160k hours)
• Score: 10.81723269312202
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scale has opened new frontiers in natural language processing, but at a high cost. In response, by learning to only activate a subset of parameters in training and inference, Mixture-of-Experts (MoE) have been proposed as an energy efficient path to even larger and more capable language models and this shift towards a new generation of foundation models is gaining momentum, particularly within the field of Automatic Speech Recognition (ASR). Recent works that incorporating MoE into ASR models have complex designs such as routing frames via supplementary embedding network, improving multilingual ability for the experts, and utilizing dedicated auxiliary losses for either expert load balancing or specific language handling. We found that delicate designs are not necessary, while an embarrassingly simple substitution of MoE layers for all Feed-Forward Network (FFN) layers is competent for the ASR task. To be more specific, we benchmark our proposed model on a large scale inner-source dataset (160k hours), the results show that we can scale our baseline Conformer (Dense-225M) to its MoE counterparts (MoE-1B) and achieve Dense-1B level Word Error Rate (WER) while maintaining a Dense-225M level Real Time Factor (RTF). Furthermore, by applying Unified 2-pass framework with bidirectional attention decoders (U2++), we achieve the streaming and non-streaming decoding modes in a single MoE based model, which we call U2++ MoE. We hope that our study can facilitate the research on scaling speech foundation models without sacrificing deployment efficiency.

Related papers

• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
  We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models. Our approach employs activation sparsity to extract experts. Read-ME outperforms other popular open-source dense models of similar scales.
  arXiv  Detail & Related papers  (2024-10-24T19:48:51Z)
• Layerwise Recurrent Router for Mixture-of-Experts [42.36093735411238]
  Mixture-of-Experts (MoE) architecture stands out for its ability to scale model size without significantly increasing training costs. Current MoE models often display parameter inefficiency. We introduce the Layerwise Recurrent Router for Mixture-of-Experts (RMoE)
  arXiv  Detail & Related papers  (2024-08-13T10:25:13Z)
• LaDiMo: Layer-wise Distillation Inspired MoEfier [1.6199400106794555]
  We propose a novel algorithm, LaDiMo, which efficiently converts a Transformer-based non-MoE model into a MoE model with minimal additional training cost. We demonstrate the effectiveness of our method by converting the LLaMA2-7B model to a MoE model using only 100K tokens.
  arXiv  Detail & Related papers  (2024-08-08T07:37:26Z)
• Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training [73.90260246781435]
  We present Lory, the first approach that scales such architectures to autoregressive language model pre-training. We show significant performance gains over parameter-matched dense models on both perplexity and a variety of downstream tasks. Despite segment-level routing, Lory models achieve competitive performance compared to state-of-the-art MoE models with token-level routing.
  arXiv  Detail & Related papers  (2024-05-06T03:06:33Z)
• 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)
• TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training [18.68993910156101]
  We propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging. We show that TA-MoE can substantially outperform its counterparts on various hardware and model configurations.
  arXiv  Detail & Related papers  (2023-02-20T11:18:24Z)
• Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models [68.9288651177564]
  We present a novel MoE architecture based on matrix product operators (MPO) from quantum many-body physics. With the decomposed MPO structure, we can reduce the parameters of the original MoE architecture. Experiments on the three well-known downstream natural language datasets based on GPT2 show improved performance and efficiency in increasing model capacity.
  arXiv  Detail & Related papers  (2022-03-02T13:44:49Z)
• 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)
• Scalable and Efficient MoE Training for Multitask Multilingual Models [55.987536562357086]
  We develop a system capable of scaling MoE models efficiently to trillions of parameters. We also present new training methods to improve MoE sample efficiency and leverage expert pruning strategy to improve time efficiency. A model trained with 10 billion parameters on 50 languages can achieve state-of-the-art performance in Machine Translation (MT) and multilingual natural language generation tasks.
  arXiv  Detail & Related papers  (2021-09-22T00:57:46Z)
• SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts [29.582683923988203]
  Mixture of Experts (MoE) based Transformer has shown promising results in many domains. In this work, we explore the MoE based model for speech recognition, named SpeechMoE. New router architecture is used in SpeechMoE which can simultaneously utilize the information from a shared embedding network.
  arXiv  Detail & Related papers  (2021-05-07T02:38:23Z)

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.