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 2306.03364cs.LGcs.CV
收藏

在单位球面上学习表示:研究在线持续学习中的角高斯分布与 von Mises-Fisher 分布

Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning

Univ Gustave Eiffel(Gustave Eiffel大学);CNRS(法国国家科学研究中心)

Nicolas Michel, Giovanni Chierchia, Romain Negrel, Jean-François Bercher

AI总结:

本文提出基于角高斯分布和 von Mises-Fisher 分布的最大后验估计方法,通过将表示推向固定先验均值方向以抵御数据漂移,并结合基于记忆的学习技术,在无需负数据或任务边界知识的情况下,显著提升了在线持续学习的性能。

摘要:

我们使用最大后验估计原理来学习分布在单位球面上的表示。我们提出使用角高斯分布,它对应于投影到单位球面上的高斯分布,并推导出相关的损失函数。我们还考虑了 von Mises-Fisher 分布,它是单位球面上高斯分布的条件分布。学习到的表示被推向固定方向,这些方向是高斯分布的先验均值;这使得学习策略能够抵御数据漂移。这使其适用于在线持续学习,即在连续数据流上训练神经网络的问题,其中多个分类任务被顺序呈现,因此过去任务的数据不再可访问,而当前任务的数据只能被看到一次。为了应对这一具有挑战性的场景,我们提出了一种配备我们新损失函数的基于记忆的表示学习技术。我们的方法不需要负数据或任务边界的知识,在较小的批量大小下表现良好,同时计算效率高。我们通过大量实验证明,所提出的方法在标准评估场景和具有模糊任务边界的现实场景中均优于当前最先进的方法。为了可复现性,我们对每个比较的方法使用相同的训练流程,并在 https://github.com/Nicolas1203/ocl-fd 分享代码。

英文摘要:

We use the maximum a posteriori estimation principle for learning representations distributed on the unit sphere. We propose to use the angular Gaussian distribution, which corresponds to a Gaussian projected on the unit-sphere and derive the associated loss function. We also consider the von Mises-Fisher distribution, which is the conditional of a Gaussian in the unit-sphere. The learned representations are pushed toward fixed directions, which are the prior means of the Gaussians; allowing for a learning strategy that is resilient to data drift. This makes it suitable for online continual learning, which is the problem of training neural networks on a continuous data stream, where multiple classification tasks are presented sequentially so that data from past tasks are no longer accessible, and data from the current task can be seen only once. To address this challenging scenario, we propose a memory-based representation learning technique equipped with our new loss functions. Our approach does not require negative data or knowledge of task boundaries and performs well with smaller batch sizes while being computationally efficient. We demonstrate with extensive experiments that the proposed method outperforms the current state-of-the-art methods on both standard evaluation scenarios and realistic scenarios with blurry task boundaries. For reproducibility, we use the same training pipeline for every compared method and share the code at https://github.com/Nicolas1203/ocl-fd.

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。

↑