真相何在?在持续变化的世界中遭遇混杂因素带来的混淆风险
Where is the Truth? The Risk of Getting Confounded in a Continual World
AI总结:
本研究针对持续学习场景中混杂因素随任务时间变化的问题,形式化描述了持续混杂因素,构建了ConCon数据集,发现标准持续学习方法无法应对混杂因素,凸显了开发相关稳健方法的必要性。
摘要:
如果一个数据集最容易通过虚假相关性求解,而这种相关性无法泛化到新数据,那么该数据集就是存在混杂的。在本研究中,我们发现,在混杂因素可能随任务时间变化的持续学习场景中,减轻混杂因素影响的挑战远超通常所考虑的标准遗忘问题。具体而言,我们对此类持续混杂因素给出了形式化描述,并指出一般而言,联合训练所有任务时虚假相关性很容易被忽略,但按顺序考虑任务时更难避免混杂。这些描述为构建一个基于CLEVR的新型持续混杂数据集奠定了基础,我们将其命名为ConCon数据集。我们的评估表明,标准的持续学习方法无法忽略该数据集的混杂因素。总体而言,我们的工作凸显了混杂因素带来的挑战,尤其是在持续学习场景中,并证明了开发能够稳健应对这些问题的持续学习方法的必要性。
英文摘要:
A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting where confounders may vary in time across tasks, the challenge of mitigating the effect of confounders far exceeds the standard forgetting problem normally considered. In particular, we provide a formal description of such continual confounders and identify that, in general, spurious correlations are easily ignored when training for all tasks jointly, but it is harder to avoid confounding when they are considered sequentially. These descriptions serve as a basis for constructing a novel CLEVR-based continually confounded dataset, which we term the ConCon dataset. Our evaluations demonstrate that standard continual learning methods fail to ignore the dataset's confounders. Overall, our work highlights the challenges of confounding factors, particularly in continual learning settings, and demonstrates the need for developing continual learning methods to robustly tackle these.
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。