# Multicriteria interpretability driven Deep Learning

arXiv: https://arxiv.org/abs/2111.14088 · HTML: https://mlsanity.com/paper/2111.14088/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 70 references that are in the map.
- First posted on arXiv 28 Nov 2021.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models](https://mlsanity.com/paper/1612.08468/) (2016)
- [Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems](https://mlsanity.com/paper/1903.12394/) (2019)
- [Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling](https://mlsanity.com/paper/1710.11431/) (2017)
- [Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges](https://mlsanity.com/paper/2010.09337/) (2020)
- [Deep Learning for Financial Applications : A Survey](https://mlsanity.com/paper/2002.05786/) (2020)
- [Fashionable Modelling with Flux](https://mlsanity.com/paper/1811.01457/) (2018)
- [Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoring](https://mlsanity.com/paper/2009.13384/) (2020)
- [Compensating data shortages in manufacturing with monotonicity knowledge](https://mlsanity.com/paper/2010.15955/) (2020)
- [Deep Learning Decoding of Mental State in Non-invasive Brain Computer Interface](https://mlsanity.com/paper/1911.05661/) (2019)
- [Data Science in Economics](https://mlsanity.com/paper/2003.13422/) (2020)
- [The JuliaConnectoR: a functionally oriented interface for integrating Julia in R](https://mlsanity.com/paper/2005.06334/) (2020)

## Built on by (most cited first, 5 of 5)

- [Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoring](https://mlsanity.com/paper/2209.10070/) (2022)
- [Generalized Groves of Neural Additive Models: Pursuing transparent and accurate machine learning models in finance](https://mlsanity.com/paper/2209.10082/) (2022)
- [Interpretable Selective Learning in Credit Risk](https://mlsanity.com/paper/2209.10127/) (2022)
- [Can I Trust the Explanations? Investigating Explainable Machine Learning Methods for Monotonic Models](https://mlsanity.com/paper/2309.13246/) (2023)
- [Explaining Risks: Axiomatic Risk Attributions for Financial Models](https://mlsanity.com/paper/2506.06653/) (2025)

## Abstract (arXiv)

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by reverse-engineering the model's inner workings. However, in many regulated fields, interpretability should be kept in mind from the start, which means that post-hoc methods are valid only as a sanity check after model training. Interpretability from the start, in an abstract setting, means posing a set of soft constraints on the model's behavior by injecting knowledge and annihilating possible biases. We propose a Multicriteria technique that allows to control the feature effects on the model's outcome by injecting knowledge in the objective function. We then extend the technique by including a non-linear knowledge function to account for more complex effects and local lack of knowledge. The result is a Deep Learning model that embodies interpretability from the start and aligns with the recent regulations. A practical empirical example based on credit risk, suggests that our approach creates performant yet robust models capable of overcoming biases derived from data scarcity.