Representation Surgery for Multi-Task Model Merging
- URL: http://arxiv.org/abs/2402.02705v2
- Date: Tue, 28 May 2024 09:35:17 GMT
- Title: Representation Surgery for Multi-Task Model Merging
- Authors: Enneng Yang, Li Shen, Zhenyi Wang, Guibing Guo, Xiaojun Chen, Xingwei Wang, Dacheng Tao,
- Abstract summary: Multi-task learning (MTL) compresses the information from multiple tasks into a unified backbone to improve computational efficiency and generalization.
Recent work directly merges multiple independently trained models to perform MTL instead of collecting their raw data for joint training.
By visualizing the representation distribution of existing model merging schemes, we find that the merged model often suffers from the dilemma of representation bias.
- Score: 57.63643005215592
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multi-task learning (MTL) compresses the information from multiple tasks into a unified backbone to improve computational efficiency and generalization. Recent work directly merges multiple independently trained models to perform MTL instead of collecting their raw data for joint training, greatly expanding the application scenarios of MTL. However, by visualizing the representation distribution of existing model merging schemes, we find that the merged model often suffers from the dilemma of representation bias. That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL. In this paper, we propose a representation surgery solution called "Surgery" to reduce representation bias in the merged model. Specifically, Surgery is a lightweight task-specific module that takes the representation of the merged model as input and attempts to output the biases contained in the representation from the merged model. We then designed an unsupervised optimization objective that updates the Surgery module by minimizing the distance between the merged model's representation and the individual model's representation. Extensive experiments demonstrate significant MTL performance improvements when our Surgery module is applied to state-of-the-art (SOTA) model merging schemes.
Related papers
- MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic [6.46176287368784]
We propose textbfModel textbfExclusive textbfTask textbfArithmetic for merging textbfGPT-scale models.
Our proposed MetaGPT is data-agnostic and bypasses the heavy search process, making it cost-effective and easy to implement for LLMs.
arXiv Detail & Related papers (2024-06-17T10:12:45Z) - MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation [80.47072100963017]
Model merging is an effective approach to combine multiple single-task models, fine-tuned from the same pre-trained model, into a multitask model.
Existing model-merging methods focus on enhancing average task accuracy.
We introduce a novel low-compute algorithm, Model Merging with Amortized Pareto Front (MAP)
arXiv Detail & Related papers (2024-06-11T17:55:25Z) - Federated Model Heterogeneous Matryoshka Representation Learning [33.04969829305812]
Model heterogeneous federated learning (MteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion.
Existing methods rely on training loss to transfer knowledge between a MteroFL server and a client model.
We propose a new representation approach for supervised learning tasks using Matryoshka models.
arXiv Detail & Related papers (2024-06-01T16:37:08Z) - DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
We propose DEEM, a simple and effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.
DEEM exhibits enhanced robustness and a superior capacity to alleviate hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
arXiv Detail & Related papers (2024-05-24T05:46:04Z) - 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) - Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously.
We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework.
The results show that our model can achieve state-of-the-art performance.
arXiv Detail & Related papers (2020-10-12T03:27:07Z)
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.