arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.08207cs.LGcs.AI
收藏

遗忘较少是正向转移的一个好的归纳偏置吗?

Is forgetting less a good inductive bias for forward transfer?

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);DeepMind(深度思维)

Jiefeng Chen, Timothy Nguyen, Dilan Gorur, Arslan Chaudhry

摘要:

研究持续学习的主要动机之一是问题设置允许模型从过去的任务中积累知识,以更有效地学习新任务。然而,最近的研究表明,持续学习算法优化的关键指标,灾难性遗忘的减少,与知识的向前转移没有很好的相关性。我们认为,以前的工作所得出的结论是由于他们的方式来衡量向前转移。我们认为,前向迁移到一个任务的措施不应该受到持续学习者的限制,以保持以前的任务的知识。相反,前向迁移应该通过学习一项新任务的难易程度来衡量,这是通过对先前任务的持续学习产生的一组表征来实现的。在这个概念下的前向转移,我们评估不同的持续学习算法的各种图像分类基准。我们的研究结果表明,较少的健忘表示导致更好的前向迁移,这表明保留过去的信息和新任务的学习效率之间有很强的相关性。此外,我们发现较少健忘的表征更多样化和歧视性相比,他们的健忘的同行。

英文摘要:

One of the main motivations of studying continual learning is that the problem setting allows a model to accrue knowledge from past tasks to learn new tasks more efficiently. However, recent studies suggest that the key metric that continual learning algorithms optimize, reduction in catastrophic forgetting, does not correlate well with the forward transfer of knowledge. We believe that the conclusion previous works reached is due to the way they measure forward transfer. We argue that the measure of forward transfer to a task should not be affected by the restrictions placed on the continual learner in order to preserve knowledge of previous tasks. Instead, forward transfer should be measured by how easy it is to learn a new task given a set of representations produced by continual learning on previous tasks. Under this notion of forward transfer, we evaluate different continual learning algorithms on a variety of image classification benchmarks. Our results indicate that less forgetful representations lead to a better forward transfer suggesting a strong correlation between retaining past information and learning efficiency on new tasks. Further, we found less forgetful representations to be more diverse and discriminative compared to their forgetful counterparts.

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。

↑