# Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection

arXiv: https://arxiv.org/abs/2006.10966 · HTML: https://mlsanity.com/paper/2006.10966/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2020.

## Built on by (most cited first, 30 of 32)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework](https://mlsanity.com/paper/2302.12247/) (2023)
- [SHAP-IQ: Unified Approximation of any-order Shapley Interactions](https://mlsanity.com/paper/2303.01179/) (2023)
- [Discovering and Explaining the Representation Bottleneck of DNNs](https://mlsanity.com/paper/2111.06236/) (2021)
- [MultiViz: Towards Visualizing and Understanding Multimodal Models](https://mlsanity.com/paper/2207.00056/) (2022)
- [AutoLoss: Automated Loss Function Search in Recommendations](https://mlsanity.com/paper/2106.06713/) (2021)
- [KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactions](https://mlsanity.com/paper/2405.10852/) (2024)
- [Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications](https://mlsanity.com/paper/2306.04539/) (2023)
- [MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts](https://mlsanity.com/paper/2311.09580/) (2023)
- [Efficient XAI Techniques: A Taxonomic Survey](https://mlsanity.com/paper/2302.03225/) (2023)
- [Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks](https://mlsanity.com/paper/2104.04488/) (2021)
- [Multimodal Fusion Interactions: A Study of Human and Automatic Quantification](https://mlsanity.com/paper/2306.04125/) (2023)
- [Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence](https://mlsanity.com/paper/2301.04020/) (2022)
- [Interpretable Artificial Intelligence through the Lens of Feature Interaction](https://mlsanity.com/paper/2103.03103/) (2021)
- [Exploring the cloud of feature interaction scores in a Rashomon set](https://mlsanity.com/paper/2305.10181/) (2023)
- [SmoothHess: ReLU Network Feature Interactions via Stein's Lemma](https://mlsanity.com/paper/2311.00858/) (2023)
- [A Comprehensive Survey on Automated Machine Learning for Recommendations](https://mlsanity.com/paper/2204.01390/) (2022)
- [Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-Experts](https://mlsanity.com/paper/2509.25678/) (2025)
- [Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability](https://mlsanity.com/paper/2305.03100/) (2023)
- [Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control](https://mlsanity.com/paper/2507.12202/) (2025)
- [Random Intersection Chains](https://mlsanity.com/paper/2104.04714/) (2021)
- [Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?](https://mlsanity.com/paper/2304.04330/) (2023)
- [Towards Assumption-free Bias Mitigation](https://mlsanity.com/paper/2307.04105/) (2023)
- [Foundations of Multisensory Artificial Intelligence](https://mlsanity.com/paper/2404.18976/) (2024)
- [How Usable is Automated Feature Engineering for Tabular Data?](https://mlsanity.com/paper/2508.13932/) (2025)
- [Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG](https://mlsanity.com/paper/2103.02405/) (2021)
- [Online Interaction Detection for Click-Through Rate Prediction](https://mlsanity.com/paper/2106.15400/) (2021)
- [CUBE: Contrastive Understanding by Balanced Experiments](https://mlsanity.com/paper/2509.10825/) (2025)

## Abstract (arXiv)

Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the predictions of black-box recommender systems. In particular, we propose to interpret feature interactions from a source recommender model and explicitly encode these interactions in a target recommender model, where both source and target models are black-boxes. By not assuming the structure of the recommender system, our approach can be used in general settings. In our experiments, we focus on a prominent use of machine learning recommendation: ad-click prediction. We found that our interaction interpretations are both informative and predictive, e.g., significantly outperforming existing recommender models. What's more, the same approach to interpret interactions can provide new insights into domains even beyond recommendation, such as text and image classification.