# Backward Compatibility in Attributive Explanation and Enhanced Model Training Method

arXiv: https://arxiv.org/abs/2408.02298 · HTML: https://mlsanity.com/paper/2408.02298/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [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)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [Machine Learning Operations (MLOps): Overview, Definition, and Architecture](https://mlsanity.com/paper/2205.02302/) (2022)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [Positive-Congruent Training: Towards Regression-Free Model Updates](https://mlsanity.com/paper/2011.09161/) (2020)
- [An Empirical Analysis of Backward Compatibility in Machine Learning Systems](https://mlsanity.com/paper/2008.04572/) (2020)
- [Order in the Court: Explainable AI Methods Prone to Disagreement](https://mlsanity.com/paper/2105.03287/) (2021)
- [MLOps -- Definitions, Tools and Challenges](https://mlsanity.com/paper/2201.00162/) (2022)
- [Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreement](https://mlsanity.com/paper/2211.08943/) (2022)
- [Comparing Explanation Methods for Traditional Machine Learning Models Part 2: Quantifying Model Explainability Faithfulness and Improvements with Dimensionality Reduction](https://mlsanity.com/paper/2211.10378/) (2022)

## Built on by (most cited first, 1 of 1)

- [Backward Compatibility in Tree-Based Explanations and Enhanced CART Algorithm](https://mlsanity.com/paper/2608.08674/) (2026)

## Abstract (arXiv)

Model update is a crucial process in the operation of ML/AI systems. While updating a model generally enhances the average prediction performance, it also significantly impacts the explanations of predictions. In real-world applications, even minor changes in explanations can have detrimental consequences. To tackle this issue, this paper introduces BCX, a quantitative metric that evaluates the backward compatibility of feature attribution explanations between pre- and post-update models. BCX utilizes practical agreement metrics to calculate the average agreement between the explanations of pre- and post-update models, specifically among samples on which both models accurately predict. In addition, we propose BCXR, a BCX-aware model training method by designing surrogate losses which theoretically lower bounds agreement scores. Furthermore, we present a universal variant of BCXR that improves all agreement metrics, utilizing L2 distance among the explanations of the models. To validate our approach, we conducted experiments on eight real-world datasets, demonstrating that BCXR achieves superior trade-offs between predictive performances and BCX scores, showcasing the effectiveness of our BCXR methods.