Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models

• URL: http://arxiv.org/abs/2409.12512v2
• Date: Fri, 20 Sep 2024 08:35:45 GMT
• Title: Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models
• Authors: Jun Rao, Xuebo Liu, Zepeng Lin, Liang Ding, Jing Li, Dacheng Tao, Min Zhang,
• Abstract summary: 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.
• Score: 62.5501109475725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. The success of KD in auto-regressive language models mainly relies on Reverse KL for mode-seeking and student-generated output (SGO) to combat exposure bias. Our theoretical analyses and experimental validation reveal that while Reverse KL effectively mimics certain features of the teacher distribution, it fails to capture most of its behaviors. Conversely, SGO incurs higher computational costs and presents challenges in optimization, particularly when the student model is significantly smaller than the teacher model. These constraints are primarily due to the immutable distribution of the teacher model, which fails to adjust adaptively to models of varying sizes. We introduce Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. This strategy abolishes the necessity for on-policy sampling and merely requires minimal updates to the parameters of the teacher's online module during training, thereby allowing dynamic adaptation to the student's distribution to make distillation better. Extensive results across multiple generation datasets show that OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.

Related papers

• Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling [81.00825302340984]
  We introduce Speculative Knowledge Distillation (SKD) to generate high-quality training data on-the-fly. In SKD, the student proposes tokens, and the teacher replaces poorly ranked ones based on its own distribution. We evaluate SKD on various text generation tasks, including translation, summarization, math, and instruction following.
  arXiv  Detail & Related papers  (2024-10-15T06:51:25Z)
• Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment [10.104085497265004]
  We propose Ranking Loss based Knowledge Distillation (RLKD), which encourages consistency of peak predictions between the teacher and student models. Our method enables the student model to better learn the multi-modal distributions of the teacher model, leading to a significant performance improvement in various downstream tasks.
  arXiv  Detail & Related papers  (2024-09-19T08:06:42Z)
• CLDA: Collaborative Learning for Enhanced Unsupervised Domain Adaptation [15.97351561456467]
  Collaborative Learning is a method that updates the teacher's non-salient parameters using the student model and at the same time enhance the student's performance. CLDA achieves an improvement of +0.7% mIoU for teacher and +1.4% mIoU for student compared to the baseline model in the GTA to Cityscapes.
  arXiv  Detail & Related papers  (2024-09-04T13:35:15Z)
• DistiLLM: Towards Streamlined Distillation for Large Language Models [53.46759297929675]
  DistiLLM is a more effective and efficient KD framework for auto-regressive language models. DisiLLM comprises two components: (1) a novel skew Kullback-Leibler divergence loss, where we unveil and leverage its theoretical properties, and (2) an adaptive off-policy approach designed to enhance the efficiency in utilizing student-generated outputs.
  arXiv  Detail & Related papers  (2024-02-06T11:10:35Z)
• Reinforced Multi-Teacher Selection for Knowledge Distillation [54.72886763796232]
  knowledge distillation is a popular method for model compression. Current methods assign a fixed weight to a teacher model in the whole distillation. Most of the existing methods allocate an equal weight to every teacher model. In this paper, we observe that, due to the complexity of training examples and the differences in student model capability, learning differentially from teacher models can lead to better performance of student models distilled.
  arXiv  Detail & Related papers  (2020-12-11T08:56:39Z)
• Ensemble Knowledge Distillation for CTR Prediction [46.92149090885551]
  We propose a new model training strategy based on knowledge distillation (KD) KD is a teacher-student learning framework to transfer knowledge learned from a teacher model to a student model. We propose some novel techniques to facilitate ensembled CTR prediction, including teacher gating and early stopping by distillation loss.
  arXiv  Detail & Related papers  (2020-11-08T23:37:58Z)
• MixKD: Towards Efficient Distillation of Large-scale Language Models [129.73786264834894]
  We propose MixKD, a data-agnostic distillation framework, to endow the resulting model with stronger generalization ability. We prove from a theoretical perspective that under reasonable conditions MixKD gives rise to a smaller gap between the error and the empirical error. Experiments under a limited-data setting and ablation studies further demonstrate the advantages of the proposed approach.
  arXiv  Detail & Related papers  (2020-11-01T18:47:51Z)

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.