arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.11629cs.LGmath.STstat.MLstat.TH
收藏

从弱监督学习到主动学习

From Weakly Supervised Learning to Active Learning

École Normale Supérieure(巴黎高等师范学院);INRIA(法国国家信息与自动化研究所);DI ENS(巴黎高等师范学院信息学系);PSL(巴黎文理研究大学);Paderborn University(帕德博恩大学);ENSAE(法国国家统计与经济管理学院);NYU(纽约大学)

Vivien Cabannes

摘要:

自从最近监督学习的成功以来,应用数学和机器计算已经带来了很多希望。许多行业从业者一直在尝试从旧范式转向机器学习。有趣的是,这些数据科学家花费更多的时间来清理,注释和清理数据,而不是微调模型。本论文的动机是以下问题:我们可以得到一个更通用的框架比之监督学习,以学习从杂乱的数据?这个问题是通过弱监督学习的镜头,假设数据汇集的瓶颈在于注释。我们将弱监管模型化为给出一组目标候选人,而不是一个唯一的目标。我们认为,应该寻找一个“乐观”的功能,匹配大多数的意见。这使我们能够推导出消除部分标签歧义的原则。我们还讨论了将无监督学习技术纳入我们的框架的优点,特别是通过扩散技术进行的流形正则化,为此我们推导出一种新的算法,该算法比基线方法更好地与输入维度相结合。最后,我们从被动转向主动弱监督学习,引入"主动标记“框架,在该框架中,从业者可以查询有关所选数据的弱信息。其中,我们利用这样一个事实,即不需要完整的信息来访问随机梯度和执行随机梯度下降。

英文摘要:

Applied mathematics and machine computations have raised a lot of hope since the recent success of supervised learning. Many practitioners in industries have been trying to switch from their old paradigms to machine learning. Interestingly, those data scientists spend more time scrapping, annotating and cleaning data than fine-tuning models. This thesis is motivated by the following question: can we derive a more generic framework than the one of supervised learning in order to learn from clutter data? This question is approached through the lens of weakly supervised learning, assuming that the bottleneck of data collection lies in annotation. We model weak supervision as giving, rather than a unique target, a set of target candidates. We argue that one should look for an ``optimistic'' function that matches most of the observations. This allows us to derive a principle to disambiguate partial labels. We also discuss the advantage to incorporate unsupervised learning techniques into our framework, in particular manifold regularization approached through diffusion techniques, for which we derived a new algorithm that scales better with input dimension then the baseline method. Finally, we switch from passive to active weakly supervised learning, introducing the ``active labeling'' framework, in which a practitioner can query weak information about chosen data. Among others, we leverage the fact that one does not need full information to access stochastic gradients and perform stochastic gradient descent.

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。

↑