arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.06173cs.LG
收藏

基于具体子空间学习的多任务模型融合干扰消除

Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

School of Computer Science, Wuhan University(武汉大学计算机学院);Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Sun Yat-sen University(中山大学);Alibaba Group(阿里巴巴集团);School of Information and Electronics, Beijing Institute of Technology(北京理工大学信息与电子学院);Nanyang Technological University(南洋理工大学)

Anke Tang, Xianglin Luo, Li Shen, Yong Luo, Liang Ding, Han Hu, Bo Du, Dacheng Tao

AI总结:

提出连续松弛离散子空间学习方法,通过元学习框架识别低维共享子空间,解决多任务模型融合中的参数冲突问题,在视觉和语言任务上验证有效性。

摘要:

从共同的大规模预训练模型微调得到但专用于不同任务的模型合并,已被证明是一种廉价且可扩展的策略,用于构建在各种任务上表现良好的多任务模型。最近的研究,以任务算术为例,强调这种多任务模型可以通过任务向量上的算术运算得到。然而,当前的融合技术通常通过评估单个属性(如参数的大小或符号)来解决任务特定模型参数之间的潜在冲突,忽略了它们对模型整体功能的集体影响。在这项工作中,我们提出了连续松弛离散(Concrete)子空间学习方法,以识别一个共同的低维子空间,并利用其共享信息来跟踪干扰问题,而不会牺牲太多性能。具体来说,我们将问题建模为双层优化问题,并引入一个元学习框架,通过基于梯度的技术找到具体的子空间掩码。在上层,我们专注于学习一个共享的具体掩码来识别子空间,而在内层,执行模型合并以最大化合并模型的性能。我们在视觉领域和语言领域进行了广泛的实验,结果证明了我们方法的有效性。代码可在以下网址获取:https://this https URL

英文摘要:

Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multi-task model that performs well across diverse tasks. Recent research, exemplified by task arithmetic, highlights that this multi-task model can be derived through arithmetic operations on task vectors. Nevertheless, current merging techniques frequently resolve potential conflicts among parameters from task-specific models by evaluating individual attributes, such as the parameters' magnitude or sign, overlooking their collective impact on the overall functionality of the model. In this work, we propose the CONtinuous relaxation of disCRETE (Concrete) subspace learning method to identify a common low-dimensional subspace and utilize its shared information to track the interference problem without sacrificing much performance. Specifically, we model the problem as a bi-level optimization problem and introduce a meta-learning framework to find the Concrete subspace mask through gradient-based techniques. At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model. We conduct extensive experiments on both vision domain and language domain, and the results demonstrate the effectiveness of our method. The code is available at https://github.com/tanganke/subspace_fusion

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑