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 2306.05331cs.AIcs.CE
收藏

利用深度侧信息主动学习贝叶斯矩阵融合模型

Actively learning a Bayesian matrix fusion model with deep side information

School of Business(商学院);Stevens Institute of Technology(史蒂文斯理工学院)

Yangyang Yu, Jordan W. Suchow

AI总结:

针对深度特征空间行为反应数据稀疏、对齐成本高的问题,提出带深度侧信息的贝叶斯矩阵分解主动学习方法,结合序贯批量采样策略,相比被动基线效率显著提升,可适配小样本实验室及大规模众包场景。

摘要:

图像与概念的高维深度神经网络表征可被对齐以预测人类对各类刺激的标注。然而,此类对齐需要成本高昂的行为反应收集,因此在实际中,深度特征空间始终仅被稀疏采样。本文提出一种主动学习方法,通过自适应采样实验刺激,高效学习带有深度侧信息的贝叶斯矩阵分解模型。我们观察到该方法相比被动基线有显著的效率提升。此外,借助序贯批量采样策略,该算法不仅适用于从传统实验室实验收集的小型数据集,还适用于需要大规模众包数据收集以准确对齐从预训练网络得到的高维深度特征表征的场景。

英文摘要:

High-dimensional deep neural network representations of images and concepts can be aligned to predict human annotations of diverse stimuli. However, such alignment requires the costly collection of behavioral responses, such that, in practice, the deep-feature spaces are only ever sparsely sampled. Here, we propose an active learning approach to adaptively sampling experimental stimuli to efficiently learn a Bayesian matrix factorization model with deep side information. We observe a significant efficiency gain over a passive baseline. Furthermore, with a sequential batched sampling strategy, the algorithm is applicable not only to small datasets collected from traditional laboratory experiments but also to settings where large-scale crowdsourced data collection is needed to accurately align the high-dimensional deep feature representations derived from pre-trained networks.

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。

↑