Explanation Mining: Post Hoc Interpretability of Latent Factor Models for Recommendation Systems

By Georgina Peake, Jun Wang. 2018

164 citations recorded by the source corpus.

The widescale use of machine learning algorithms to drive decision-making has highlighted the critical importance of ensuring the interpretability of such models in order to engender trust in their output. The state-of-the-art recommendation systems use black-box latent factor models that provide no explanation of why a recommendation has been made, as they abstract their decision processes to a high-dimensional latent space which is beyond the direct comprehension of humans. We propose a novel approach for extracting explanations from latent factor recommendation systems by training association rules on the output of a matrix factorisation black-box model. By taking advantage of the interpretable structure of association rules, we demonstrate that predictive accuracy of the recommendation model can be maintained whilst yielding explanations with high fidelity to the black-box model on a unique industry dataset. Our approach mitigates the accuracy-interpretability trade-off whilst avoiding the need to sacrifice flexibility or use external data sources. We also contribute to the ill-defined problem of evaluating interpretability.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “In this sense, Peake and Wang [2018] can be considered as a pointwise post-hoc explanation model, while Singh and Anand [2018] can be considered as a pair-wise or list-wise post-hoc explanation model.”
Co-Attentive Multi-Task Learning for Explainable Recommendation (2019, methodology): “Post-hoc methods explain a black-box model after it is trained [Vig et al., 2009; Sharma and Cosley, 2013; Peake and Wang, 2018].”
A historical perspective of explainable Artificial Intelligence (2020, background): “A different approach to explaining the performance of a recommender engine is to consider it as a black-box that can be probed so as to extract statistical features of recommendations (Peake & Wang, 2018).”
Trust in AI: progress, challenges, and future directions (2024, unknown): “Post-hoc interpretable methods refer to methods that utilize the power of complex black-box models in accurate predictions and try to add global or local interpretability to their decisions (Du et al., 2019; Madsen et al., 2021; Molnar et al., 2019; Peake and Wang, 2018).”
Explainable Recommendation through Attentive Multi-View Learning (2019, methodology): “Thus, many methods have been developed to improve the explainabil-ity of recommendation models (Ren et al. 2017; Peake and Wang 2018; Wang et al. 2018b).”
A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, unknown): “The others compromise slightly: they design post-hoc separate models to explain the results generated by łblack boxž recommender systems, e.g., Explanation Mining [142].”