# Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

arXiv: https://arxiv.org/abs/2007.06133 · HTML: https://mlsanity.com/paper/2007.06133/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems](https://mlsanity.com/paper/2110.14844/) (2021)
- [Interpretability-Aware Vision Transformer](https://mlsanity.com/paper/2309.08035/) (2023)
- [Negative Flux Aggregation to Estimate Feature Attributions](https://mlsanity.com/paper/2301.06989/) (2023)
- [Towards Explainable Collaborative Filtering with Taste Clusters Learning](https://mlsanity.com/paper/2304.13937/) (2023)
- [Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation](https://mlsanity.com/paper/2210.12693/) (2022)
- [Explaining Recommendation System Using Counterfactual Textual Explanations](https://mlsanity.com/paper/2303.11160/) (2023)
- [Conv4Rec: A 1-by-1 Convolutional AutoEncoder for User Profiling through Joint Analysis of Implicit and Explicit Feedbacks](https://mlsanity.com/paper/2509.07499/) (2025)
- [PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN](https://mlsanity.com/paper/2502.12207/) (2025)

## Abstract (arXiv)

Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items. Recently, explainable recommendation has attracted much attention from research community. However, trade-off exists between explainability and performance of the recommendation where metadata is often needed to alleviate the dilemma. We present a novel feature mapping approach that maps the uninterpretable general features onto the interpretable aspect features, achieving both satisfactory accuracy and explainability in the recommendations by simultaneous minimization of rating prediction loss and interpretation loss. To evaluate the explainability, we propose two new evaluation metrics specifically designed for aspect-level explanation using surrogate ground truth. Experimental results demonstrate a strong performance in both recommendation and explaining explanation, eliminating the need for metadata. Code is available from https://github.com/pd90506/AMCF.