GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model

• URL: http://arxiv.org/abs/2406.09444v2
• Date: Fri, 21 Jun 2024 08:48:41 GMT
• Title: GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model
• Authors: Yingying Gao, Shilei Zhang, Chao Deng, Junlan Feng,
• Abstract summary: This paper introduces GenDistiller, a novel knowledge distillation framework which generates the hidden representations of the pre-trained teacher model directly by a much smaller student network. The proposed method takes the previous hidden layer as history and implements a layer-by-layer prediction of the teacher model autoregressively. Experiments reveal the advantage of GenDistiller over the baseline distilling method without an autoregressive framework, with 33% fewer parameters, similar time consumption and better performance on most of the SUPERB tasks.
• Score: 20.620589404103644
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high requirements for memory and computing resource hinder their application on resource restricted devices. Therefore, this paper introduces GenDistiller, a novel knowledge distillation framework which generates the hidden representations of the pre-trained teacher model directly by a much smaller student network. The proposed method takes the previous hidden layer as history and implements a layer-by-layer prediction of the teacher model autoregressively. Experiments on SUPERB reveal the advantage of GenDistiller over the baseline distilling method without an autoregressive framework, with 33% fewer parameters, similar time consumption and better performance on most of the SUPERB tasks. Ultimately, the proposed GenDistiller reduces the size of WavLM by 82%.

Related papers

• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion [29.297959023968165]
  This paper proposes a progressive distillation method based on masked generation features for KGC task. Specifically, we perform pre-distillation on PLM to obtain high-quality teacher models, and compress the PLM network to obtain multi-grade student models. The experimental results demonstrate that the model in the pre-distillation stage surpasses the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-19T07:34:36Z)
• Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition [5.802425107635222]
  Miniaturization for SSL models has become an important research direction of practical value. We explore the effective distillation of HuBERT-based SSL models for automatic speech recognition (ASR) A discriminative loss is introduced for HuBERT to enhance the distillation performance, especially in low-resource scenarios.
  arXiv  Detail & Related papers  (2022-10-27T17:21:14Z)
• Few-shot Prompting Towards Controllable Response Generation [49.479958672988566]
  We first explored the combination of prompting and reinforcement learning (RL) to steer models' generation without accessing any of the models' parameters. We apply multi-task learning to make the model learn to generalize to new tasks better. Experiment results show that our proposed method can successfully control several state-of-the-art (SOTA) dialogue models without accessing their parameters.
  arXiv  Detail & Related papers  (2022-06-08T14:48:06Z)
• MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation [68.30497162547768]
  We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed. We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks.
  arXiv  Detail & Related papers  (2022-04-15T23:19:37Z)
• Improving Non-autoregressive Generation with Mixup Training [51.61038444990301]
  We present a non-autoregressive generation model based on pre-trained transformer models. We propose a simple and effective iterative training method called MIx Source and pseudo Target. Our experiments on three generation benchmarks including question generation, summarization and paraphrase generation, show that the proposed framework achieves the new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-10-21T13:04:21Z)
• bert2BERT: Towards Reusable Pretrained Language Models [51.078081486422896]
  We propose bert2BERT, which can effectively transfer the knowledge of an existing smaller pre-trained model to a large model. bert2BERT saves about 45% and 47% computational cost of pre-training BERT_BASE and GPT_BASE by reusing the models of almost their half sizes.
  arXiv  Detail & Related papers  (2021-10-14T04:05:25Z)
• Self-Feature Regularization: Self-Feature Distillation Without Teacher Models [0.0]
  Self-Feature Regularization(SFR) is proposed, which uses features in the deep layers to supervise feature learning in the shallow layers. We firstly use generalization-l2 loss to match local features and a many-to-one approach to distill more intensively in the channel dimension.
  arXiv  Detail & Related papers  (2021-03-12T15:29:00Z)
• Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones [40.33419553042038]
  We propose to improve existing baseline networks via knowledge distillation from off-the-shelf pre-trained big powerful models. Our solution performs distillation by only driving prediction of the student model consistent with that of the teacher model. We empirically find that such simple distillation settings perform extremely effective, for example, the top-1 accuracy on ImageNet-1k validation set of MobileNetV3-large and ResNet50-D can be significantly improved.
  arXiv  Detail & Related papers  (2021-03-10T09:32:44Z)
• Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation [55.34995029082051]
  We propose a method to learn to augment for data-scarce domain BERT knowledge distillation. We show that the proposed method significantly outperforms state-of-the-art baselines on four different tasks.
  arXiv  Detail & Related papers  (2021-01-20T13:07:39Z)

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.