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 2010.13015cs.LGstat.ML
收藏

基于神经网络拓扑分析的交互检测

Towards Interaction Detection Using Topological Analysis on Neural Networks

Texas A&M University(得克萨斯农工大学);Tencent Company(腾讯公司)

Zirui Liu, Qingquan Song, Kaixiong Zhou, Ting Hsiang Wang, Ying Shan, Xia Hu

摘要:

检测输入特征之间的统计相互作用是一项至关重要且具有挑战性的任务。最近的进展表明,从训练好的神经网络中提取学习到的交互是可能的。人们还观察到,在神经网络中,任何相互作用的特征必须遵循一个强加权连接到共同的隐藏单元。受此启发,本文提出从一个新的拓扑角度,通过分析神经网络的连通性来研究交互检测问题。特别是,我们提出了一个新的措施来量化的相互作用强度,持久同源性理论的基础上广受好评。在此基础上,提出了一种持久性交互检测算法(PID).我们提出的算法在几个合成和现实世界的数据集上使用不同的超参数进行交互检测任务的评估。实验结果验证了PID算法优于最先进的基线。

英文摘要:

Detecting statistical interactions between input features is a crucial and challenging task. Recent advances demonstrate that it is possible to extract learned interactions from trained neural networks. It has also been observed that, in neural networks, any interacting features must follow a strongly weighted connection to common hidden units. Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. Based on this measure, a Persistence Interaction detection~(PID) algorithm is developed to efficiently detect interactions. Our proposed algorithm is evaluated across a number of interaction detection tasks on several synthetic and real world datasets with different hyperparameters. Experimental results validate that the PID algorithm outperforms the state-of-the-art baselines.

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。

↑