mlsanityData to 7 Oct 2026

Stability of Explainable Recommendation

arXiv 2405.01849 ↗First posted 3 May 2024cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Explainable Recommendation has been gaining attention over the last few years in industry and academia. Explanations provided along with recommendations in a recommender system framework have many uses: particularly reasoning why a suggestion is provided and how well an item aligns with a user's personalized preferences. Hence, explanations can play a huge role in influencing users to purchase products. However, the reliability of the explanations under varying scenarios has not been strictly verified from an empirical perspective. Unreliable explanations can bear strong consequences such as attackers leveraging explanations for manipulating and tempting users to purchase target items that the attackers would want to promote. In this paper, we study the vulnerability of existent feature-oriented explainable recommenders, particularly analyzing their performance under different levels of external noises added into model parameters. We conducted experiments by analyzing three important state-of-the-art (SOTA) explainable recommenders when trained on two widely used e-commerce based recommendation datasets of different scales. We observe that all the explainable models are vulnerable to increased noise levels. Experimental results verify our hypothesis that the ability to explain recommendations does decrease along with increasing noise levels and particularly adversarial noise does contribute to a much stronger decrease. Our study presents an empirical verification on the topic of robust explanations in recommender systems which can be extended to different types of explainable recommenders in RS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

33 of 49 references.

References · 33

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  3. 2018Sanity Checks for Saliency Mapscited by 1,149
  4. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  5. 2017Interpretation of Neural Networks is Fragilecited by 443
  6. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  7. 2018On the Robustness of Interpretability Methodscited by 310
  8. 2019Explanations can be manipulated and geometry is to blamecited by 215
  9. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  10. 2019Explainable Machine Learning in Deploymentcited by 210
  11. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  12. 2018Interpretable Deep Learning under Firecited by 74
21 more
  1. 2021Counterfactual Explainable Recommendationcited by 60
  2. 2021Personalized Transformer for Explainable Recommendationcited by 58
  3. 2022Rethinking Stability for Attribution-based Explanationscited by 52
  4. 2021Knowledge-aware Coupled Graph Neural Network for Social Recommendationcited by 49
  5. 2018Adversarial Personalized Ranking for Recommendationcited by 48
  6. 2021Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networkscited by 48
  7. 2018Explainable Recommendation via Multi-Task Learning in Opinionated Text Datacited by 40
  8. 2022A Survey on Trustworthy Recommender Systemscited by 40
  9. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  10. 2020Try This Instead: Personalized and Interpretable Substitute Recommendationcited by 34
  11. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  12. 2020Analyzing the Noise Robustness of Deep Neural Networkscited by 31
  13. 2019Bridging Adversarial Robustness and Gradient Interpretabilitycited by 22
  14. 2022Trustworthy Recommender Systemscited by 21
  15. 2021Jointly Attacking Graph Neural Network and its Explanationscited by 18
  16. 2022Explainable Fairness in Recommendationcited by 15
  17. 2019Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendationcited by 9
  18. 2021From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systemscited by 9
  19. 2019Adversarial Mahalanobis Distance-based Attentive Song Recommender for Automatic Playlist Continuationcited by 4
  20. 2019White Noise Analysis of Neural Networkscited by 4
  21. 2022Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systemscited by 1

Built on by

Not cited yet.