分布条件任务路由用于类增量学习

中文摘要 AI 辅助

参数高效适配使得持续学习者能够通过紧凑的模型更新获取任务特定知识，同时保持强大的任务内性能。然而，类增量推理要求每个输入在所有已见类别中进行分类，且无法访问其任务身份。对于配备任务特定参数高效模块的学习者，这引入了超越灾难性遗忘的关键任务路由挑战。我们研究无需重新训练学习者或引入单独训练路由器的后验任务路由。这种免训练的推理时校准在参数高效类增量学习中相对未被充分探索。我们识别了三种路由错误来源（特征级、任务级和类级错位），并提出了特征分布校准（FDC）。其三个组件分别解决这些错位：任务子空间过滤（TSF）抑制每个任务主子空间之外的特征成分，残差似然校准（RLC）评估其子空间残差的典型性，原型亲和力校准（PAC）衡量与任务类原型的兼容性。实验表明，FDC可即插即用地应用于使用共享编码器的八种参数高效类增量方法。在全部五个基准上为每种方法选择一个组件配置，FDC在所有40个方法-数据集组合中将最终准确率平均提升4.39个百分点。启用所有组件改善了40个组合中的35个，平均提升4.45个百分点。当应用于简单基线时，FDC实现了强大的整体性能。

英文摘要

Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong within-task performance. However, class-incremental inference requires each input to be classified among all classes seen so far without access to its task identity. For learners equipped with task-specific parameter-efficient modules, this introduces a critical task-routing challenge beyond catastrophic forgetting. We study post-hoc task routing without retraining the learner or introducing a separately trained router. Such training-free inference-time calibration remains comparatively underexplored in parameter-efficient class-incremental learning. We identify three sources of routing error (feature-level, task-level, and class-level misalignment) and propose Feature Distribution Calibration (FDC). Its three components address these misalignments: Task Subspace Filtering (TSF) suppresses feature components outside each task's principal subspace, Residual Likelihood Calibration (RLC) evaluates the typicality of its subspace residual, and Prototype Affinity Calibration (PAC) measures compatibility with the task's class prototypes. Experiments demonstrate plug-and-play applicability to eight parameter-efficient class-incremental methods using a shared encoder. With one component configuration selected per method across all five benchmarks, FDC improves final accuracy in all 40 method-dataset pairs by 4.39 percentage points on average. Enabling all components improves 35 of the 40 pairs, with an average gain of 4.45 points. When applied to a simple baseline, FDC achieves strong overall performance.

发表机构

• Nanjing University（南京大学）
• Nanyang Technological University（南洋理工大学）
• Shanghai Jiao Tong University（上海交通大学）

机构由 AI 辅助整理，请以论文原文为准。