提出RI方法，通过解耦模型降低任务干扰，提升合并效果。
Resolving Interference (RI): Disentangling Models for Improved Model Merging
- 用无标签数据解耦专家模型，使其在任务空间正交
- 相比现有方法性能最高提升3.8%，跨域泛化提升2.3%
- 无需任务数据，对超参数不敏感，适合数据稀缺场景
模型合并已证明可通过直接结合各自专注特定任务的模型参数，构建多任务模型。然而，独立训练的不同任务模型常出现干扰，导致合并后性能下降。为此，我们正式定义了跨任务干扰为合并模型表征相对于原始模型的偏移。减少跨任务干扰是提升合并性能的关键。本文提出轻量级适配框架Resolving Interference（RI），通过将专家模型解耦至与其他任务空间正交，从而降低干扰。该方法仅需无标签辅助数据输入（无需任务数据），适用于数据稀缺场景。实验表明，RI可使当前最优合并方法性能提升高达3.8%，跨域泛化能力提升达2.3%。此外，RI对辅助输入来源鲁棒，且显著降低对合并超参数的敏感性。代码已开源。
原文摘要 · Abstract (English)
Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of interest. However, models trained independently on distinct tasks often exhibit interference that degrades the merged model's performance. To solve this problem, we formally define the notion of Cross-Task Interference as the drift in the representation of the merged model relative to its constituent models. Reducing cross-task interference is key to improving merging performance. To address this issue, we propose our method, Resolving Interference (RI), a light-weight adaptation framework which disentangles expert models to be functionally orthogonal to the space of other tasks, thereby reducing cross-task interference. RI does this whilst using only unlabeled auxiliary data as input (i.e., no task-data is needed), allowing it to be applied in data-scarce scenarios. RI consistently improves the performance of state-of-the-art merging methods by up to 3.8% and generalization to unseen domains by up to 2.3%. We also find RI to be robust to the source of auxiliary input while being significantly less sensitive to tuning of merging hyperparameters. Our codebase is available at: https://github.com/pramesh39/resolving_interference
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。