We present CLEAR, a method for learning session-specific causal graphs, in
the possible presence of latent confounders, from attention in pre-trained
attention-based recommenders. These causal graphs describe user behavior,
within the context captured by attention, and can provide a counterfactual
explanation for a recommendation. In essence, these causal graphs allow
answering "why" questions uniquely for any specific session. Using empirical
evaluations we show that, compared to naively using attention weights to
explain input-output relations, counterfactual explanations found by CLEAR are
shorter and an alternative recommendation is ranked higher in the original
top-k recommendations.

本文介绍了 CLEAR 方法，它可以从基于注意力的推荐器的注意力中学习会话特定的因果图，在潜在混淆因素的可能存在下进行。这些因果关系图描述了用户在注意力所捕捉到的上下文中的行为，并为推荐提供了反事实的解释。通过实证评估，我们发现与天真地使用注意力权重来解释输入输出关系相比，CLEAR 找到的反事实解释更简短，并且替代推荐在原始的 Top-K 推荐中得到了更高的排名。