面向终身学习的任务难度感知参数分配与正则化
Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
AI总结：
本文提出PAR方法，根据任务学习难度在参数分配与正则化之间自适应选择策略，并通过最近原型距离估计任务相关性和高效的架构搜索降低参数冗余，在多个基准上超越SOTA并提升性能。
摘要：
参数正则化或参数分配方法在克服终身学习中的灾难性遗忘方面是有效的。然而，它们以统一的方式顺序求解所有任务，并忽略了不同任务在学习难度上的差异。因此，当学习一个与已学任务差异很大的新任务时，参数正则化方法面临严重的遗忘问题，而参数分配方法在学习简单任务时面临不必要的参数开销。在本文中，我们提出了参数分配与正则化（PAR）方法，该方法根据每个任务的学习难度，在参数分配和参数正则化之间自适应地选择合适的策略。对于一个已经学习过与其相关任务的模型来说，该任务是容易的，反之亦然。我们提出了一种基于最近原型距离的散度估计方法，仅利用新任务的特征来衡量任务相关性。此外，我们提出了一种时间高效的相关性感知的基于采样的架构搜索策略，以减少参数分配带来的参数开销。在多个基准上的实验结果表明，与SOTA方法相比，我们的方法具有可扩展性，并显著降低了模型的冗余度，同时提升了模型的性能。进一步的定性分析表明，PAR能够获得合理的任务相关性。
英文摘要：
Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and ignore the differences in the learning difficulty of different tasks. So parameter regularization methods face significant forgetting when learning a new task very different from learned tasks, and parameter allocation methods face unnecessary parameter overhead when learning simple tasks. In this paper, we propose the Parameter Allocation & Regularization (PAR), which adaptively select an appropriate strategy for each task from parameter allocation and regularization based on its learning difficulty. A task is easy for a model that has learned tasks related to it and vice versa. We propose a divergence estimation method based on the Nearest-Prototype distance to measure the task relatedness using only features of the new task. Moreover, we propose a time-efficient relatedness-aware sampling-based architecture search strategy to reduce the parameter overhead for allocation. Experimental results on multiple benchmarks demonstrate that, compared with SOTAs, our method is scalable and significantly reduces the model's redundancy while improving the model's performance. Further qualitative analysis indicates that PAR obtains reasonable task-relatedness.
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。
