# Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction

arXiv: https://arxiv.org/abs/2008.11406 · HTML: https://mlsanity.com/paper/2008.11406/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [A Consistent and Efficient Evaluation Strategy for Attribution Methods](https://mlsanity.com/paper/2202.00449/) (2022)
- [A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps](https://mlsanity.com/paper/2106.03819/) (2021)
- [Explainability in Music Recommender Systems](https://mlsanity.com/paper/2201.10528/) (2022)
- [Towards Rigorous Interpretations: a Formalisation of Feature Attribution](https://mlsanity.com/paper/2104.12437/) (2021)
- [Recommender Systems: A Primer](https://mlsanity.com/paper/2302.02579/) (2023)
- [Context-aware feature attribution through argumentation](https://mlsanity.com/paper/2310.16157/) (2023)

## Abstract (arXiv)

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key to check the sanity and robustness of a decision process and improve their efficiency, it however remains a challenge for complex architectures, especially deep neural networks that are often deemed "black-box". In this paper, we propose a novel formulation of interpretable deep neural networks for the attribution task. Differently to popular post-hoc methods, our approach is interpretable by design. Using masked weights, hidden features can be deeply attributed, split into several input-restricted sub-networks and trained as a boosted mixture of experts. Experimental results on synthetic data and real-world recommendation tasks demonstrate that our method enables to build models achieving close predictive performances to their non-interpretable counterparts, while providing informative attribution interpretations.