arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.02153cs.LGcs.AIcs.DScs.GTcs.NE
收藏

围合博弈中分类器的Shapley值

The Shapley Value of Classifiers in Ensemble Games

The University of Edinburgh(爱丁堡大学)

Benedek Rozemberczki, Rik Sarkar

摘要:

在二元分类器的集合中,单个模型的价值是什么?我们回答这个问题,通过引入一类可转移的效用合作博弈称为\textit{ensemble games}。在机器学习集成中,预先训练的模型合作做出分类决策。为了量化模型在这些集成游戏中的重要性,我们定义了\textit{Troupe} -一种有效的算法,该算法根据分类器的近似Shapley值分配收益。我们认为,在这些游戏中的模型的Shapley值是一个有效的决策度量选择一个高性能的子集的模型从合奏。我们的分析结果证明,我们的Shapley值估计方案是精确的和可扩展的;其性能随着数据集和集成的大小而增加。对真实世界图分类任务的实证结果表明,我们的算法产生高质量的Shapley值的估计。我们发现Shapley值可以用于集成修剪,并且对抗模型的估值较低。复杂的分类器经常被发现负责正确和不正确的分类决策。

英文摘要:

What is the value of an individual model in an ensemble of binary classifiers? We answer this question by introducing a class of transferable utility cooperative games called \textit{ensemble games}. In machine learning ensembles, pre-trained models cooperate to make classification decisions. To quantify the importance of models in these ensemble games, we define \textit{Troupe} -- an efficient algorithm which allocates payoffs based on approximate Shapley values of the classifiers. We argue that the Shapley value of models in these games is an effective decision metric for choosing a high performing subset of models from the ensemble. Our analytical findings prove that our Shapley value estimation scheme is precise and scalable; its performance increases with size of the dataset and ensemble. Empirical results on real world graph classification tasks demonstrate that our algorithm produces high quality estimates of the Shapley value. We find that Shapley values can be utilized for ensemble pruning, and that adversarial models receive a low valuation. Complex classifiers are frequently found to be responsible for both correct and incorrect classification decisions.

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。

↑