Why Train Everything? Tint a Single Layer for Multi-task Model Merging

• URL: http://arxiv.org/abs/2412.19098v2
• Date: Sun, 09 Mar 2025 04:21:56 GMT
• Title: Why Train Everything? Tint a Single Layer for Multi-task Model Merging
• Authors: Aecheon Jung, Seunghwan Lee, Dongyoon Han, Sungeun Hong,
• Abstract summary: Model merging integrates independently fine-tuned models into a single multi-task model, offering a flexible alternative to joint training.<n>Many existing model merging methods introduce additional task-specific components, increasing complexity and requiring extra modifications.<n>We propose Model Tinting, a lightweight yet highly effective approach that improves model merging by updating just a single layer.
• Score: 17.496018757317824
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model merging integrates independently fine-tuned models into a single multi-task model, offering a flexible alternative to joint training. However, many existing model merging methods introduce additional task-specific components, increasing complexity and requiring extra modifications. We propose Model Tinting, a lightweight yet highly effective approach that improves model merging by updating just a single layer, accounting for as low as 0.5% of total parameters. Our key observation is that explicit task-specific modules are not necessary; instead, subtle adjustments to a single layer can effectively capture task-specific variations within the merged model while maintaining generalization. We introduce a confidence-based filtering mechanism to alleviate the impact of unreliable predictions from individual models on the merged model. Extensive experiments across vision and NLP tasks demonstrate that Model Tinting achieves state-of-the-art performance, even in challenging dense prediction tasks. Our code is available at https://github.com/AIM-SKKU/ModelTinting

Related papers

• No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces [17.69597528370121]
  Model merging integrates the weights of multiple task-specific models into a single multi-task model. Despite recent interest in the problem, a significant performance gap between the combined and single-task models remains. We show that alignment between singular components of task-specific and merged matrices strongly correlates with performance improvement.
  arXiv  Detail & Related papers  (2025-02-07T14:22:56Z)
• 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. We find existing methods inevitably discard task-specific information that, while causing conflicts, is crucial for performance. 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)
• SuperMerge: An Approach For Gradient-Based Model Merging [9.136320029568305]
  Large language models, such as ChatGPT, Claude, or LLaMA, are gigantic, monolithic, and possess the superpower to simultaneously support thousands of tasks. One challenge of using task-specific models is the incremental need for solving newer tasks after the model is already deployed for existing tasks. We propose a model merging based approach called SUPERMERGE. We experimentally demonstrate that SUPERMERGE outperforms existing model merging methods on common natural language processing and computer vision tasks.
  arXiv  Detail & Related papers  (2024-12-09T20:03:14Z)
• Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization [7.776434991976473]
  Multi-Task Learning (MTL) involves the concurrent training of multiple tasks.<n>We propose an advanced MTL model specifically designed for dense vision tasks.
  arXiv  Detail & Related papers  (2024-12-04T10:05:47Z)
• Task Weighting through Gradient Projection for Multitask Learning [5.5967570276373655]
  In multitask learning, conflicts between task gradients are a frequent issue degrading a model's training performance. In this work, we present a method to adapt the Gradient Projection algorithm PCGrad to simultaneously perform task prioritization. Our approach differs from traditional task weighting performed by scaling task losses in that our weighting scheme applies only in cases where tasks are in conflict, but lets the training proceed unhindered otherwise.
  arXiv  Detail & Related papers  (2024-09-03T11:17:44Z)
• 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)
• 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)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• ZipIt! Merging Models from Different Tasks without Training [20.2479633507354]
  "ZipIt!" is a general method for merging two arbitrary models of the same architecture. We find that these two changes combined account for 20-60% improvement over prior work.
  arXiv  Detail & Related papers  (2023-05-04T17:59:58Z)
• eP-ALM: Efficient Perceptual Augmentation of Language Models [70.47962271121389]
  We propose to direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. We show that by freezing more than 99% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning.
  arXiv  Detail & Related papers  (2023-03-20T19:20:34Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Task Adaptive Parameter Sharing for Multi-Task Learning [114.80350786535952]
  Adaptive Task Adapting Sharing (TAPS) is a method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.
  arXiv  Detail & Related papers  (2022-03-30T23:16:07Z)
• Multi-Task Learning as a Bargaining Game [63.49888996291245]
  In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Since the gradients of these different tasks may conflict, training a joint model for MTL often yields lower performance than its corresponding single-task counterparts. We propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update.
  arXiv  Detail & Related papers  (2022-02-02T13:21:53Z)
• Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks [73.63892022944198]
  We present a generic perception architecture named Uni-Perceiver. It processes a variety of modalities and tasks with unified modeling and shared parameters. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks.
  arXiv  Detail & Related papers  (2021-12-02T18:59:50Z)
• Conflict-Averse Gradient Descent for Multi-task Learning [56.379937772617]
  A major challenge in optimizing a multi-task model is the conflicting gradients. We introduce Conflict-Averse Gradient descent (CAGrad) which minimizes the average loss function. CAGrad balances the objectives automatically and still provably converges to a minimum over the average loss.
  arXiv  Detail & Related papers  (2021-10-26T22:03:51Z)
• Multi-Task Learning with Sequence-Conditioned Transporter Networks [67.57293592529517]
  We aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. We propose a new suite of benchmark aimed at compositional tasks, MultiRavens, which allows defining custom task combinations. Second, we propose a vision-based end-to-end system architecture, Sequence-Conditioned Transporter Networks, which augments Goal-Conditioned Transporter Networks with sequence-conditioning and weighted sampling.
  arXiv  Detail & Related papers  (2021-09-15T21:19:11Z)
• Rethinking Hard-Parameter Sharing in Multi-Task Learning [20.792654758645302]
  Hard parameter sharing in multi-task learning (MTL) allows tasks to share some of model parameters, reducing storage cost and improving prediction accuracy. The common sharing practice is to share bottom layers of a deep neural network among tasks while using separate top layers for each task. Using separate bottom-layer parameters could achieve significantly better performance than the common practice.
  arXiv  Detail & Related papers  (2021-07-23T17:26:40Z)

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.