Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment

• URL: http://arxiv.org/abs/2409.12545v1
• Date: Thu, 19 Sep 2024 08:06:42 GMT
• Title: Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment
• Authors: Tianyu Peng, Jiajun Zhang,
• Abstract summary: 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.
• Score: 10.104085497265004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs causes difficulties for student models to learn. In this paper, we first demonstrate the importance of multi-modal distribution alignment with experiments and then highlight the inefficiency of existing KD approaches in learning multi-modal distributions. To address this problem, we propose Ranking Loss based Knowledge Distillation (RLKD), which encourages the consistency of the ranking of peak predictions between the teacher and student models. By incorporating word-level ranking loss, we ensure excellent compatibility with existing distillation objectives while fully leveraging the fine-grained information between different categories in peaks of two predicted distribution. Experimental results demonstrate that 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.

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)
• 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)
• Multi-Granularity Semantic Revision for Large Language Model Distillation [66.03746866578274]
  We propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation strategy. At the token level, we design a distribution adaptive clipping Kullback-Leibler loss as the distillation objective function. At the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent.
  arXiv  Detail & Related papers  (2024-07-14T03:51:49Z)
• Direct Preference Knowledge Distillation for Large Language Models [73.50849692633953]
  We propose Direct Preference Knowledge Distillation (DPKD) for large language models (LLMs) We re-formulate KD of LLMs into two stages: first optimizing and objective consisting of implicit reward and reverse KL divergence. We prove the value and effectiveness of the introduced implicit reward and output preference in KD through experiments and theoretical analysis.
  arXiv  Detail & Related papers  (2024-06-28T09:23:40Z)
• Unlock the Power: Competitive Distillation for Multi-Modal Large Language Models [17.25135606956287]
  Competitive Multi-modal Distillation framework (CoMD) captures bidirectional feedback between teacher and student models. Our experimental analysis of diverse datasets shows that our knowledge transfer method consistently improves the capabilities of the student model.
  arXiv  Detail & Related papers  (2023-11-14T14:49:46Z)
• Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models [51.5543321122664]
  This paper investigates how to better leverage large-scale pre-trained uni-modal models to enhance discriminative multi-modal learning. We introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA)
  arXiv  Detail & Related papers  (2023-10-08T15:01:54Z)
• Modality-specific Distillation [30.190082262375395]
  We propose modality-specific distillation (MSD) to effectively transfer knowledge from a teacher on multimodal datasets. Our idea aims at mimicking a teacher's modality-specific predictions by introducing an auxiliary loss term for each modality. Because each modality has different importance for predictions, we also propose weighting approaches for the auxiliary losses.
  arXiv  Detail & Related papers  (2021-01-06T05:45:07Z)
• 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)
• Online Knowledge Distillation via Multi-branch Diversity Enhancement [15.523646047674717]
  We propose a new distillation method to enhance the diversity among multiple student models. We use Feature Fusion Module (FFM), which improves the performance of the attention mechanism in the network. We also use Diversification(CD) loss function to strengthen the differences between the student models.
  arXiv  Detail & Related papers  (2020-10-02T05:52:12Z)

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.