arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.03522cs.LG
收藏

协同自适应多任务LoRA:领域参与的迁移感知、无标签控制

Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation

Sichuan University(四川大学);University of Electronic Science and Technology of China(电子科技大学)

Wei Zhang, Lin Tang, Ming Zhao, Yuxuan Wang

AI总结:

研究多任务学习中领域如何共享低秩适配器,提出CoDA控制器,利用无标签探针数据生成能力信号和跨域亲和力,通过求解熵正则化二次规划设置领域参与度,提升多任务学习性能。

摘要:

一次性在多个领域微调单个低秩适配器即多任务学习,多数高效微调管道忽略领域间相互影响。本文展示无需标签即可廉价得出领域参与度答案。通过当前共享适配器在小的无标签探针上的前向传播生成能力信号和跨域亲和力,据此构建CoDA控制器,提升多任务学习性能并证明相关特性。

英文摘要:

Fine-tuning a single low-rank adapter on many domains at once is multi-task learning: the domains must be co-learned, and how they share the adapter decides whether they help or hurt one another. Most efficient fine-tuning pipelines ignore this and train on a fixed, uniform mixture, leaving two coupled questions unanswered: how much should each domain participate, and which domains should be co-trained given that some transfer positively and others interfere? We show that both answers can be read off cheaply and without labels. A forward pass of the current shared adapter over a small unlabeled probe yields, per domain, a competence signal whose level tracks remaining headroom and whose trajectory tracks learning speed; the drift of these probe representations yields a signed cross-domain affinity that predicts pairwise transfer. We fold both into CoDA, a co-adaptive controller that solves a small entropy-regularized quadratic program on the simplex to set each domain's participation -- jointly its loss weight and its share of the sampled data -- rewarding high-headroom, still-learning, mutually synergistic domains and damping interfering ones. The controller is forward-only, adds no trainable parameters, and wraps any multi-task LoRA pipeline. Across five heterogeneous domains and two backbones, CoDA improves the average over uniform mixing, learned mixtures, gradient-surgery multi-task optimizers, and online data selection while using half the data, and lowers cross-domain gradient conflict. We prove that the competence signal tracks domain risk, that the participation program has a unique fixed point reached by a contraction, and that its solution performs transfer-aware water-filling; analysis, ablations, and controls corroborate each claim.

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。

↑