Scalable Model Merging with Progressive Layer-wise Distillation

• URL: http://arxiv.org/abs/2502.12706v2
• Date: Tue, 27 May 2025 05:56:07 GMT
• Title: Scalable Model Merging with Progressive Layer-wise Distillation
• Authors: Jing Xu, Jiazheng Li, Jingzhao Zhang,
• Abstract summary: We introduce a novel few-shot merging algorithm, ProDistill (Progressive Layer-wise Distillation)<n>We show that ProDistill achieves state-of-the-art performance, with up to 6.14% and 6.61% improvements in vision and NLU tasks.
• Score: 17.521794641817642
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, particularly when none or few data are available. This paper first highlights the necessity of domain-specific data for model merging by proving that data-agnostic algorithms can have arbitrarily bad worst-case performance. Building on this theoretical insight, we explore the relationship between model merging and distillation, introducing a novel few-shot merging algorithm, ProDistill (Progressive Layer-wise Distillation). Unlike common belief that layer wise training hurts performance, we show that layer-wise teacher-student distillation not only enhances the scalability but also improves model merging performance. We conduct extensive experiments to show that compared to existing few-shot merging methods, ProDistill achieves state-of-the-art performance, with up to 6.14% and 6.61% improvements in vision and NLU tasks. Furthermore, we extend the experiments to models with over 10B parameters, showcasing the exceptional scalability of ProDistill.

Related papers

• EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding [50.29046178980637]
  EpiCoDe is a method that boosts model performance in data-scarcity scenarios without extra training.<n>We show that EpiCoDe consistently outperforms existing methods with significant and robust improvement.
  arXiv  Detail & Related papers  (2025-06-04T02:11:54Z)
• Dual-Expert Consistency Model for Efficient and High-Quality Video Generation [57.33788820909211]
  We propose a parameter-efficient textbfDual-Expert Consistency Model(DCM), where a semantic expert focuses on learning semantic layout and motion, while a detail expert specializes in fine detail refinement.<n>Our approach achieves state-of-the-art visual quality with significantly reduced sampling steps, demonstrating the effectiveness of expert specialization in video diffusion model distillation.
  arXiv  Detail & Related papers  (2025-06-03T17:55:04Z)
• Why Do More Experts Fail? A Theoretical Analysis of Model Merging [51.18155031364046]
  Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model.<n>Recent model merging methods have shown promising results, but struggle to maintain performance gains as the number of merged models increases.<n>We show that the limited effective parameter space imposes a strict constraint on the number of models that can be successfully merged.
  arXiv  Detail & Related papers  (2025-05-27T14:10:46Z)
• Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer [17.463052541838504]
  Fine-tuned models often struggle outside their specific domains and exhibit considerable redundancy.<n>Recent studies suggest that combining a pruned fine-tuned model with the original pre-trained model can mitigate interference when merging model parameters across tasks.<n>We introduce a novel method called Neural Pruning (NPS-Pruning) for slimming down fine-tuned models.
  arXiv  Detail & Related papers  (2025-05-24T14:27:20Z)
• Extrapolation Merging: Keep Improving With Extrapolation and Merging [14.786100203787194]
  Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. Model merging aims to enhance performance by combining the parameters of different models. We propose Extrapolation Merging, a paradigm that can continue improving model performance without requiring extra computational resources or data.
  arXiv  Detail & Related papers  (2025-03-05T14:28:22Z)
• Multi-Level Collaboration in Model Merging [56.31088116526825]
  This paper explores the intrinsic connections between model merging and model ensembling. We find that even when previous restrictions are not met, there is still a way for model merging to attain a near-identical and superior performance similar to that of ensembling.
  arXiv  Detail & Related papers  (2025-03-03T07:45:04Z)
• Improved Training Technique for Latent Consistency Models [18.617862678160243]
  Consistency models are capable of producing high-quality samples in either a single step or multiple steps.<n>We analyze the statistical differences between pixel and latent spaces, discovering that latent data often contains highly impulsive outliers.<n>We introduce a diffusion loss at early timesteps and employ optimal transport (OT) coupling to further enhance performance.
  arXiv  Detail & Related papers  (2025-02-03T15:25:58Z)
• Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [74.02034188307857]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.<n>We find existing methods inevitably discard task-specific information that, while causing conflicts, is crucial for performance.<n>Our approach consistently outperforms previous methods, achieving state-of-the-art results across diverse architectures and tasks in both vision and NLP domains.
  arXiv  Detail & Related papers  (2025-01-02T12:45:21Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning [21.693779973263172]
  In this paper, we introduce a fine-tuning approach termed Feature Discrimination Alignment (FD-Align) Our method aims to bolster the model's generalizability by preserving the consistency of spurious features. Once fine-tuned, the model can seamlessly integrate with existing methods, leading to performance improvements.
  arXiv  Detail & Related papers  (2023-10-23T17:12:01Z)
• AdaMerging: Adaptive Model Merging for Multi-Task Learning [68.75885518081357]
  This paper introduces an innovative technique called Adaptive Model Merging (AdaMerging) It aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data. Compared to the current state-of-the-art task arithmetic merging scheme, AdaMerging showcases a remarkable 11% improvement in performance.
  arXiv  Detail & Related papers  (2023-10-04T04:26:33Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• Contrastive Model Inversion for Data-Free Knowledge Distillation [60.08025054715192]
  We propose Contrastive Model Inversion, where the data diversity is explicitly modeled as an optimizable objective. Our main observation is that, under the constraint of the same amount of data, higher data diversity usually indicates stronger instance discrimination. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that CMI achieves significantly superior performance when the generated data are used for knowledge distillation.
  arXiv  Detail & Related papers  (2021-05-18T15:13:00Z)

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.