ATM: Improving Model Merging by Alternating Tuning and Merging

• URL: http://arxiv.org/abs/2411.03055v4
• Date: Fri, 08 Aug 2025 14:13:09 GMT
• Title: ATM: Improving Model Merging by Alternating Tuning and Merging
• Authors: Luca Zhou, Daniele Solombrino, Donato Crisostomi, Maria Sofia Bucarelli, Fabrizio Silvestri, Emanuele Rodolà,
• Abstract summary: We provide a theoretical motivation for task vectors by highlighting that, under single-epoch full-batch gradient descent, they are equivalent to multitask.<n>This insight leads us to reinterpret model merging as a single step in an iterative procedure that Alternates between Tuning and Merging.<n>We propose two applications of ATM: (1) as an alternative to multitask learning in scenarios where data sharing is restricted, and (2) as a lightweight refinement step to improve existing model merging methods using a small validation set.
• Score: 16.12778778313037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors by highlighting that, under single-epoch full-batch gradient descent, they are equivalent to multitask gradients. This insight leads us to reinterpret model merging as a single step in an iterative procedure that Alternates between Tuning and Merging (ATM). We propose two applications of ATM: (1) as an alternative to multitask learning in scenarios where data sharing is restricted (e.g., federated settings), and (2) as a lightweight refinement step to improve existing model merging methods using a small validation set. Experiments across diverse vision tasks demonstrate the effectiveness of ATM.

Related papers

• Model Merging in the Essential Subspace [78.5390284258307]
  Model merging aims to integrate multiple task-specific fine-tuned models into a single multi-task model without additional training.<n>Despite extensive research, task interference remains a major obstacle that often undermines the performance of merged models.<n>We propose ESM (Essential Subspace Merging), a robust framework for effective model merging.
  arXiv  Detail & Related papers  (2026-02-23T00:33:38Z)
• Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation [5.461305353111217]
  We introduce task-specific multi-task adaptation, a novel parameter-efficient approach for multi-task learning.<n>Our approach achieves better relative improvement to single-task fine-tuning while reducing the number of trainable parameters.
  arXiv  Detail & Related papers  (2025-09-23T21:51:04Z)
• Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration [14.503741632243646]
  Multi-task model merging aims to consolidate knowledge from multiple task-specific experts into a unified model.<n>Existing methods approach this by minimizing differences between task-specific experts and the unified model.<n>We propose Layer-wise Optimal Task Vector Merging, a technique that explicitly minimizes feature drift between task-specific experts and the unified model.
  arXiv  Detail & Related papers  (2025-05-29T08:11:31Z)
• Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning [59.6658995479243]
  We propose texttext-Perturb-and-Merge (P&M), a novel continual learning framework that integrates model merging into the CL paradigm to avoid forgetting.<n>Through theoretical analysis, we minimize the total loss increase across all tasks and derive an analytical solution for the optimal merging coefficient.<n>Our proposed approach achieves state-of-the-art performance on several continual learning benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-28T14:14:19Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning [46.51245338355645]
  Model merging is a flexible and computationally tractable approach to merge single-task checkpoints into a multi-task model.<n>We show that it qualitatively differs from the single-input-multiple-output model merging settings studied in the literature due to the existence of task-specific decoders.<n>We propose two simple and efficient fixes for the SIMO setting to re-align the feature representation after merging.
  arXiv  Detail & Related papers  (2025-04-15T15:10:46Z)
• Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning [59.001091197106085]
  Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously.<n>Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and in tegrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning.<n>We propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner.
  arXiv  Detail & Related papers  (2025-01-12T17:41:23Z)
• Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent [72.10987117380584]
  Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data.<n>We find existing methods 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)
• Multi-Task Model Merging via Adaptive Weight Disentanglement [69.7292615212444]
  We introduce an Adaptive Weight Disentanglement method for model merging. We successfully extract redundant vectors, and after their subtraction, the task vectors retain robust performance.
  arXiv  Detail & Related papers  (2024-11-27T20:08:55Z)
• Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate [105.86576388991713]
  We introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives. We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets.
  arXiv  Detail & Related papers  (2024-10-29T14:41:44Z)
• Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity [16.643892206707854]
  Grad-TAG can estimate task affinities without repeatedly training on data from various task combinations. We show that Grad-TAG achieves excellent performance and runtime tradeoffs compared to existing approaches.
  arXiv  Detail & Related papers  (2024-09-09T21:59:27Z)
• Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning [39.4348419684885]
  Multi-task learning (MTL) aims at learning a single model that solves several tasks efficiently. We introduce a novel gradient aggregation approach using Bayesian inference. We empirically demonstrate the benefits of our approach in a variety of datasets.
  arXiv  Detail & Related papers  (2024-02-06T14:00:43Z)
• Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning [19.850893012601638]
  Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. We propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning.
  arXiv  Detail & Related papers  (2023-11-26T01:44:01Z)
• 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)
• FAMO: Fast Adaptive Multitask Optimization [48.59232177073481]
  We introduce Fast Adaptive Multitask Optimization FAMO, a dynamic weighting method that decreases task losses in a balanced way. Our results indicate that FAMO achieves comparable or superior performance to state-of-the-art gradient manipulation techniques.
  arXiv  Detail & Related papers  (2023-06-06T15:39:54Z)
• ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning [59.08197876733052]
  Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks. Sometimes, learning multiple tasks simultaneously results in lower accuracy than learning only the target task, known as negative transfer. ForkMerge is a novel approach that periodically forks the model into multiple branches, automatically searches the varying task weights.
  arXiv  Detail & Related papers  (2023-01-30T02:27:02Z)
• Multi-task Highly Adaptive Lasso [1.4680035572775534]
  We propose a novel, fully nonparametric approach for the multi-task learning, the Multi-task Highly Adaptive Lasso (MT-HAL) MT-HAL simultaneously learns features, samples and task associations important for the common model, while imposing a shared sparse structure among similar tasks. We show that MT-HAL outperforms sparsity-based MTL competitors across a wide range of simulation studies.
  arXiv  Detail & Related papers  (2023-01-27T23:46:57Z)
• 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)
• 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)
• Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent [79.58680275615752]
  We propose an energy-efficient federated meta-learning framework. We assume each task is owned by a separate agent, so a limited number of tasks is used to train a meta-model.
  arXiv  Detail & Related papers  (2021-05-31T08:15:44Z)
• Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference [75.95287293847697]
  Two common challenges in developing multi-task models are often overlooked in literature. First, enabling the model to be inherently incremental, continuously incorporating information from new tasks without forgetting the previously learned ones (incremental learning) Second, eliminating adverse interactions amongst tasks, which has been shown to significantly degrade the single-task performance in a multi-task setup (task interference)
  arXiv  Detail & Related papers  (2020-07-24T14:44:46Z)

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.