arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2102.06253cs.LG
收藏

Continuum:复杂持续学习场景的简单管理

Continuum: Simple Management of Complex Continual Learning Scenarios

Sorbonne Université(索邦大学);Heuritech(Heuritech公司);Université de Montréal(蒙特利尔大学);Mila - Quebec AI Institute(米拉-魁北克人工智能研究所)

Arthur Douillard, Timothée Lesort

摘要:

持续学习是一个专门用于非iid数据设置的机器学习子领域。因此,训练数据分布不是静态的并且随时间漂移。这些漂移可能会对训练模型造成干扰,并且可能会忘记在数据分布的先前状态上学习的知识。持续学习的挑战是创建能够在处理数据分布漂移的同时学习不断增长的知识量的算法。这些领域的一个实现困难是创建模拟非iid场景的数据加载器。事实上,数据加载器是连续算法的关键组件。它们应该是精心设计和可复制的。数据加载器中的小错误会对算法结果产生关键影响,例如预处理不当、数据顺序错误或测试集错误。Continuum是一个简单而高效的框架,具有大量的数据加载器,避免了研究人员花费时间设计数据加载器,消除了耗时的错误。使用我们提出的框架,可以通过使用多个场景和实现的评估指标来直接关注模型设计。此外,该框架很容易扩展,以添加新的设置,以满足特定的需求。

英文摘要:

Continual learning is a machine learning sub-field specialized in settings with non-iid data. Hence, the training data distribution is not static and drifts through time. Those drifts might cause interferences in the trained model and knowledge learned on previous states of the data distribution might be forgotten. Continual learning's challenge is to create algorithms able to learn an ever-growing amount of knowledge while dealing with data distribution drifts. One implementation difficulty in these field is to create data loaders that simulate non-iid scenarios. Indeed, data loaders are a key component for continual algorithms. They should be carefully designed and reproducible. Small errors in data loaders have a critical impact on algorithm results, e.g. with bad preprocessing, wrong order of data or bad test set. Continuum is a simple and efficient framework with numerous data loaders that avoid researcher to spend time on designing data loader and eliminate time-consuming errors. Using our proposed framework, it is possible to directly focus on the model design by using the multiple scenarios and evaluation metrics implemented. Furthermore the framework is easily extendable to add novel settings for specific needs.

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。

↑