Learning Post-Hoc Causal Explanations for Recommendation [article]

Shuyuan Xu, Yunqi Li, Shuchang Liu, Zuohui Fu, Xu Chen, Yongfeng Zhang
<span title="2021-02-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
State-of-the-art recommender systems have the ability to generate high-quality recommendations, but usually cannot provide intuitive explanations to humans due to the usage of black-box prediction models. The lack of transparency has highlighted the critical importance of improving the explainability of recommender systems. In this paper, we propose to extract causal rules from the user interaction history as post-hoc explanations for the black-box sequential recommendation mechanisms, whilst
more &raquo; ... intain the predictive accuracy of the recommendation model. Our approach firstly achieves counterfactual examples with the aid of a perturbation model, and then extracts personalized causal relationships for the recommendation model through a causal rule mining algorithm. Experiments are conducted on several state-of-the-art sequential recommendation models and real-world datasets to verify the performance of our model on generating causal explanations. Meanwhile, We evaluate the discovered causal explanations in terms of quality and fidelity, which show that compared with conventional association rules, causal rules can provide personalized and more effective explanations for the behavior of black-box recommendation models.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16977v2">arXiv:2006.16977v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ngtmfbgzvat7cgvsitm5r25hu">fatcat:2ngtmfbgzvat7cgvsitm5r25hu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210227092258/https://arxiv.org/pdf/2006.16977v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4d/2d/4d2d6603744f30fd4d7652ae015e1d2bcf8a786b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16977v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>