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 2408.07718cs.LGcs.AI
收藏

不准确污染率对鲁棒无监督异常检测的影响

Impact of Inaccurate Contamination Ratio on Robust Unsupervised Anomaly Detection

University of Sherbrooke(谢尔布鲁克大学);University of Kinshasa(金沙萨大学)

Jordan F. Masakuna, DJeff Kanda Nkashama, Arian Soltani, Marc Frappier, Pierre-Martin Tardif, Froduald Kabanza

AI总结:

本研究针对无监督异常检测中污染率常不准确的问题,探究其对鲁棒无监督异常检测模型的影响,经6个基准数据集验证,模型不受错误污染率的不利影响,甚至性能可能提升。

摘要:

用于无监督异常检测的训练数据集通常被假定为无异常,但实际上往往包含异常(即污染),这一挑战会严重削弱模型性能。多数鲁棒无监督异常检测模型依赖污染率信息来应对污染问题,但现实中污染率可能并不准确。我们研究了不准确的污染率信息对鲁棒无监督异常检测的影响,验证这类模型对错误的污染率是否具有恢复能力。我们在6个基准数据集上开展的研究表明,这类模型不会因接触错误信息而受到不利影响;实际上,当提供此类不准确的污染率时,它们的性能还可能有所提升。

英文摘要:

Training data sets intended for unsupervised anomaly detection, typically presumed to be anomaly-free, often contain anomalies (or contamination), a challenge that significantly undermines model performance. Most robust unsupervised anomaly detection models rely on contamination ratio information to tackle contamination. However, in reality, contamination ratio may be inaccurate. We investigate on the impact of inaccurate contamination ratio information in robust unsupervised anomaly detection. We verify whether they are resilient to misinformed contamination ratios. Our investigation on 6 benchmark data sets reveals that such models are not adversely affected by exposure to misinformation. In fact, they can exhibit improved performance when provided with such inaccurate contamination ratios.

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。

↑