Unsupervised Lifelong Learning with Curricula
Unsupervised Lifelong Learning with Curricula
复制标题
DOI：
10.1145/3442381.3449839
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Yi He;Sheng Chen;Baijun Wu;Xu Yuan;Xindong Wu
中科院分区：
文献类型：
--
作者：
Yi He;Sheng Chen;Baijun Wu;Xu Yuan;Xindong Wu
终身机器学习（LML）推动了广泛的Web应用程序的开发，使部署在Web服务器上的学习系统能够以增量方式处理一系列任务。这样的系统可以在知识库中保留来自学习任务的知识，并无缝地应用它来改进未来的学习。不幸的是，大多数现有的LML方法在每个任务中都需要标签，而为所有未来的任务提供持久的人工标记是昂贵的，繁重的，容易出错的，因此是不切实际的。出于这种情况，我们提出了一个新的范式命名为无监督终身学习课程（ULLC），其中只有一个任务需要标记为初始化和系统，然后执行终身学习的后续任务在一个无监督的方式。实现这种范式的一个主要挑战在于负知识转移的发生，其中部分旧知识变得不利于学习给定的任务，但不能被学习者过滤掉没有标签的帮助。为了克服这一挑战，我们从人类的学习行为中汲取见解。具体来说，当我们面对一个困难的任务，不能很好地解决我们现有的知识，我们通常推迟它和工作的一些更容易的任务，这使我们能够增长我们的知识。此后，一旦我们回到推迟的任务，我们更有可能解决它，因为我们现在更有知识。ULLC的核心思想是相似的-在任何时候，候选任务池都根据它们与知识库的距离组织在课程中。然后，学习者从较近的任务开始，通过学习这些任务来积累知识，并通过逐渐增加的知识库来学习较远的任务。我们的建议的可行性和有效性得到证实，通过广泛的实证研究合成和真实的数据集。
Lifelong machine learning (LML) has driven the development of extensive web applications, enabling the learning systems deployed on web servers to deal with a sequence of tasks in an incremental fashion. Such systems can retain knowledge from learned tasks in a knowledge base and seamlessly apply it to improve the future learning. Unfortunately, most existing LML methods require labels in every task, whereas providing persistent human labeling for all future tasks is costly, onerous, error-prone, and hence impractical. Motivated by this situation, we propose a new paradigm named unsupervised lifelong learning with curricula (ULLC), where only one task needs to be labeled for initialization and the system then performs lifelong learning for subsequent tasks in an unsupervised fashion. A main challenge of realizing this paradigm lies in the occurrence of negative knowledge transfer, where partial old knowledge becomes detrimental for learning a given task yet cannot be filtered out by the learner without the help of labels. To overcome this challenge, we draw insights from the learning behaviors of humans. Specifically, when faced with a difficult task that cannot be well tackled by our current knowledge, we usually postpone it and work on some easier tasks first, which allows us to grow our knowledge. Thereafter, once we go back to the postponed task, we are more likely to tackle it well as we are more knowledgeable now. The key idea of ULLC is similar – at any time, a pool of candidate tasks are organized in a curriculum by their distances to the knowledge base. The learner then starts from the closer tasks, accumulates knowledge from learning them, and moves to learn the faraway tasks with a gradually augmented knowledge base. The viability and effectiveness of our proposal are substantiated through extensive empirical studies on both synthetic and real datasets.