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 2108.05018cs.IR
收藏

神经网络排名模型是鲁棒的吗?

Are Neural Ranking Models Robust?

Chen Wu, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng

摘要:

最近,我们已经见证了神经排序模型在信息检索(IR)领域的蓬勃发展。到目前为止,已经投入了大量的精力来开发有效的神经排名模型,这些模型可以很好地推广新数据。对鲁棒性的关注较少。与有效性不同,鲁棒性更关心系统在最坏情况下或恶意操作下的性能。当一项新技术进入实际应用时,不仅要知道它的平均工作方式,还要知道它在异常情况下的表现。因此,我们在这项工作中提出了一个问题:神经排名模型是否鲁棒?为了回答这个问题,首先,我们需要澄清我们在IR中谈论排名模型的鲁棒性时所指的是什么。我们表明鲁棒性实际上是一个多维概念,在IR中有三种方法来定义它:1)独立同分布(I.I.D.)下的性能方差。设置; 2)分布外(OOD)的可推广性; 3)对抗性操作的防御能力。后两个定义可以进一步分别指定为两个不同的视角,总共导致5个鲁棒性任务。基于这一分类,我们建立了相应的基准数据集,设计了实证实验,并系统地分析了几个代表性的神经排名模型对传统的概率排名模型和学习排名(LTR)模型的鲁棒性。实证结果表明,我们的问题没有简单的答案。虽然神经排名模型在大多数情况下对其他IR模型的鲁棒性较差,但其中一些仍然可以赢得五分之一的任务。这是第一次全面研究神经排名模型的鲁棒性。

英文摘要:

Recently, we have witnessed the bloom of neural ranking models in the information retrieval (IR) field. So far, much effort has been devoted to developing effective neural ranking models that can generalize well on new data. There has been less attention paid to the robustness perspective. Unlike the effectiveness which is about the average performance of a system under normal purpose, robustness cares more about the system performance in the worst case or under malicious operations instead. When a new technique enters into the real-world application, it is critical to know not only how it works in average, but also how would it behave in abnormal situations. So we raise the question in this work: Are neural ranking models robust? To answer this question, firstly, we need to clarify what we refer to when we talk about the robustness of ranking models in IR. We show that robustness is actually a multi-dimensional concept and there are three ways to define it in IR: 1) The performance variance under the independent and identically distributed (I.I.D.) setting; 2) The out-of-distribution (OOD) generalizability; and 3) The defensive ability against adversarial operations. The latter two definitions can be further specified into two different perspectives respectively, leading to 5 robustness tasks in total. Based on this taxonomy, we build corresponding benchmark datasets, design empirical experiments, and systematically analyze the robustness of several representative neural ranking models against traditional probabilistic ranking models and learning-to-rank (LTR) models. The empirical results show that there is no simple answer to our question. While neural ranking models are less robust against other IR models in most cases, some of them can still win 1 out of 5 tasks. This is the first comprehensive study on the robustness of neural ranking models.

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。

↑