一个适配器解决所有问题：迈向步不平衡类增量学习的统一表示
One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning
AI总结：
One-A通过不对称融合适配器解决步不平衡类增量学习中的任务更新问题，实现高效且稳定的模型更新。
摘要：
类增量学习（CIL）旨在随着时间的推移获取新类，同时保留先前知识，但大多数设置和方法假设任务流平衡。实际上，每个任务中的类数往往差异显著。我们称之为步不平衡，其中包含更多类的大型任务主导学习，而小型任务注入不稳定的更新。现有CIL方法假设任务平衡，因此将所有任务视为统一，产生不平衡的更新，从而降低整体学习性能。为了解决这一挑战，我们提出了One-A，一个统一且步不平衡感知的框架，逐步将任务更新合并到一个适配器中，保持恒定的推理成本。One-A通过不对称子空间对齐来保留从大型任务中学习到的主导子空间，同时约束低信息更新在其中。信息自适应加权平衡基础和新适配器之间的贡献，并通过方向门控机制选择性地融合每个奇异方向的更新，保持头部方向的稳定性并在尾部方向保持可塑性。在多个基准和步不平衡流中，One-A实现了与显著低推理开销相竞争的准确率，表明一个单一的、不对称融合的适配器既能适应动态任务大小，又能在部署时保持高效。
英文摘要：
Class-incremental learning (CIL) aims to acquire new classes over time while retaining prior knowledge, yet most setups and methods assume balanced task streams. In practice, the number of classes per task often varies significantly. We refer to this as step imbalance, where large tasks that contain more classes dominate learning and small tasks inject unstable updates. Existing CIL methods assume balanced tasks and therefore treat all tasks uniformly, producing imbalanced updates that degrade overall learning performance. To address this challenge, we propose One-A, a unified and imbalance-aware framework that incrementally merges task updates into a single adapter, maintaining constant inference cost. One-A performs asymmetric subspace alignment to preserve dominant subspaces learned from large tasks while constraining low-information updates within them. An information-adaptive weighting balances the contribution between base and new adapters, and a directional gating mechanism selectively fuses updates along each singular direction, maintaining stability in head directions and plasticity in tail ones. Across multiple benchmarks and step-imbalanced streams, One-A achieves competitive accuracy with significantly low inference overhead, showing that a single, asymmetrically fused adapter can remain both adaptive to dynamic task sizes and efficient at deployment.
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。
