FREE-Merging: Fourier Transform for Efficient Model Merging

• URL: http://arxiv.org/abs/2411.16815v2
• Date: Tue, 25 Mar 2025 16:19:52 GMT
• Title: FREE-Merging: Fourier Transform for Efficient Model Merging
• Authors: Shenghe Zheng, Hongzhi Wang,
• Abstract summary: We propose FR-Merging, an innovative method that effectively filters harmful frequency domain interference on the backbone with minimal computational overhead.<n>Free-Merging (FR-Merging with experts) strikes a balanced trade-off between training cost, inference latency, storage requirements, and performance.<n>We demonstrate the effectiveness of both FR-Merging and FREE-Merging on multiple tasks across CV, NLP, and Multi-Modal domains.
• Score: 4.7478239658886325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid growth of deep learning, there is an increasing availability of open-source models for various tasks. However, single fine-tuned models often fall short of meeting the diverse needs of users. Model merging has thus emerged as an efficient method to integrate the capabilities of existing models into a unified model. Nevertheless, existing model merging methods face challenging trade-offs between performance and deployment costs, primarily due to task interference. For the first time, we reveal that task interference is evident in the frequency domain of model parameters, yet current efforts only focus on spatial domain solutions, which are largely ineffective in addressing frequency domain interference. To mitigate the impact of frequency domain interference, we propose FR-Merging, an innovative method that effectively filters harmful frequency domain interference on the backbone with minimal computational overhead. Since performance loss is inevitable with cost-free methods, we propose a lightweight task-specific expert module that dynamically compensates for information loss during merging. This proposed framework, FREE-Merging (FR-Merging with experts), strikes a balanced trade-off between training cost, inference latency, storage requirements, and performance. We demonstrate the effectiveness of both FR-Merging and FREE-Merging on multiple tasks across CV, NLP, and Multi-Modal domains and show that they can be flexibly adapted to specific needs.

Related papers

• Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models [66.57755931421285]
  Large-scale artificial intelligence (LAI) models pose significant challenges for real-time communication scenarios.<n>This paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models.<n>We propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference.
  arXiv  Detail & Related papers  (2025-06-16T08:42:16Z)
• Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging [38.12136955174922]
  Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage.<n>Recent works explore model merging to combine multiple task-specific models into a single multi-task model without additional training.<n>Existing merging methods often fail for models fine-tuned with low-rank adaptation (LoRA), due to significant performance degradation.
  arXiv  Detail & Related papers  (2025-05-28T23:28:12Z)
• The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks [56.37880529653111]
  The demand for large computation model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications.<n>In this paper, we investigate the LAIM-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment.
  arXiv  Detail & Related papers  (2025-05-14T08:18:55Z)
• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations [12.79899622986449]
  textbfPTMRec is a novel framework that bridges the domain gap between pre-trained models and recommendation systems. This framework not only eliminates the need for costly additional pre-training but also flexibly accommodates various parameter-efficient tuning methods.
  arXiv  Detail & Related papers  (2025-02-21T15:50:14Z)
• Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging [11.708743111945727]
  Large Language Models (LLMs) have demonstrated impressive capabilities, but their high computational costs pose challenges for customization. Model merging offers a cost-effective alternative, yet existing methods suffer from interference among parameters, leading to performance degradation. We propose Optimal Brain Iterative Merging, a novel method designed to mitigate both intra-model and inter-model interference.
  arXiv  Detail & Related papers  (2025-02-17T09:07:49Z)
• Parameter-Efficient Interventions for Enhanced Model Merging [0.7373617024876725]
  Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. We propose IntervMerge, a novel approach to multi-task model merging that effectively mitigates representation bias across the model. We show that IntervMerge consistently outperforms the state-of-the-art approaches using fewer parameters.
  arXiv  Detail & Related papers  (2024-12-22T13:58:12Z)
• FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion [63.609399000712905]
  Inference at a scaled resolution leads to repetitive patterns and structural distortions. We propose two simple modules that combine to solve these issues. Our method, coined Fam diffusion, can seamlessly integrate into any latent diffusion model and requires no additional training.
  arXiv  Detail & Related papers  (2024-11-27T17:51:44Z)
• R-MTLLMF: Resilient Multi-Task Large Language Model Fusion at the Wireless Edge [78.26352952957909]
  Multi-task large language models (MTLLMs) are important for many applications at the wireless edge, where users demand specialized models to handle multiple tasks efficiently. The concept of model fusion via task vectors has emerged as an efficient approach for combining fine-tuning parameters to produce an MTLLM. In this paper, the problem of enabling edge users to collaboratively craft such MTLMs via tasks vectors is studied, under the assumption of worst-case adversarial attacks.
  arXiv  Detail & Related papers  (2024-11-27T10:57:06Z)
• Reprogramming Foundational Large Language Models(LLMs) for Enterprise Adoption for Spatio-Temporal Forecasting Applications: Unveiling a New Era in Copilot-Guided Cross-Modal Time Series Representation Learning [0.0]
  patio-temporal forecasting plays a crucial role in various sectors such as transportation systems, logistics, and supply chain management. We introduce a hybrid approach that combines the strengths of open-source large and small-scale language models (LLMs and LMs) with traditional forecasting methods.
  arXiv  Detail & Related papers  (2024-08-26T16:11:53Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging [21.918559935122786]
  Model merging is a promising way to combine multiple task-specific models into a single multitask model without extra training. Traditional model merging methods often show significant performance gaps compared to fine-tuned models. We show that both shared and exclusive task-specific knowledge are crucial for merging performance, but directly merging exclusive knowledge hinders overall performance. We propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input.
  arXiv  Detail & Related papers  (2024-06-17T02:31:55Z)
• FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation [32.305134875959226]
  Federated learning (FL) is a privacy-preserving paradigm that enables distributed clients to collaboratively train models with a central server. We propose FedHPL, a parameter-efficient unified $textbfFed$erated learning framework for $textbfH$eterogeneous settings. We show that our framework outperforms state-of-the-art FL approaches, with less overhead and training rounds.
  arXiv  Detail & Related papers  (2024-05-27T15:25:32Z)
• 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)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts [64.94129594112557]
  Merging Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. We propose to merge most of the parameters while upscaling the Transformer layers to a weight-ensembling mixture of experts (MoE) module.
  arXiv  Detail & Related papers  (2024-02-01T08:58:57Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• 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)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• TIES-Merging: Resolving Interference When Merging Models [95.59265307318752]
  Transfer learning can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. Model merging has emerged as a solution to combine multiple task-specific models into a single model without performing additional training. Existing merging methods often ignore the interference between parameters of different models, resulting in large performance drops when merging multiple models. We propose TIES-Merging, which introduces three novel steps when merging models: resetting parameters that only changed a small amount during fine-tuning, resolving sign conflicts, and merging only the parameters that are in alignment with the final agreed-upon sign.
  arXiv  Detail & Related papers  (2023-06-02T17:31:32Z)
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning [11.076005074172516]
  reinforcement learning algorithms can easily encounter catastrophic forgetting or interference when faced with lifelong streaming information. We propose a scalable lifelong RL method that dynamically expands the network capacity to accommodate new knowledge. We show that our method successfully facilitates scalable lifelong RL and outperforms relevant existing methods.
  arXiv  Detail & Related papers  (2022-05-22T09:48:41Z)
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy [142.5983499872664]
  In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement.
  arXiv  Detail & Related papers  (2021-06-20T13:51:18Z)
• Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning [56.94644428312295]
  Wireless connectivity is instrumental in enabling federated learning (FL) Channel randomnessperturbs each worker inversions model update while multiple workers updates incur significant interference on bandwidth. In A-FADMM, all workers upload their model updates to the parameter server using a single channel via analog transmissions. This not only saves communication bandwidth, but also hides each worker's exact model update trajectory from any eavesdropper.
  arXiv  Detail & Related papers  (2020-07-03T16:31:15Z)

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.