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 1806.07171cs.CV
收藏

基于排序的嵌入式系统在评估嵌入时的不确定性行为

Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings

Anguelos Nicolaou, Sounak Dey, Vincent Christlein, Andreas Maier, Dimosthenis Karatzas

摘要:

将数据嵌入向量空间是模式识别方法中一种非常流行的策略。当嵌入之间的距离被量化时,性能指标变得模糊不清。在本文中,我们提出了一个分析的模糊性量化距离介绍和提供的影响范围。我们证明,它可以有一个可衡量的影响,在国家的最先进的系统的经验数据。我们还从计算机安全的角度来处理这种现象,并演示了如何被第三方评估的人可以利用这种模糊性,并大大优于随机预测,甚至没有访问输入数据。我们还提出了一个简单的解决方案,使性能指标,这依赖于排名,完全确定性和不受这种漏洞。

英文摘要:

Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits.

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。

↑