# SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]

arXiv: https://arxiv.org/abs/2301.09559 · HTML: https://mlsanity.com/paper/2301.09559/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Visualizing Deep Neural Network Decisions: Prediction Difference Analysis](https://mlsanity.com/paper/1702.04595/) (2017)
- [Abduction-Based Explanations for Machine Learning Models](https://mlsanity.com/paper/1811.10656/) (2018)
- [A Symbolic Approach to Explaining Bayesian Network Classifiers](https://mlsanity.com/paper/1805.03364/) (2018)
- [Bayesian Compression for Deep Learning](https://mlsanity.com/paper/1705.08665/) (2017)
- [Fooling Neural Network Interpretations via Adversarial Model Manipulation](https://mlsanity.com/paper/1902.02041/) (2019)
- [Convolutional neural networks with low-rank regularization](https://mlsanity.com/paper/1511.06067/) (2015)
- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [Argumentative XAI: A Survey](https://mlsanity.com/paper/2105.11266/) (2021)
- [Hessian-Aware Pruning and Optimal Neural Implant](https://mlsanity.com/paper/2101.08940/) (2021)
- [Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)](https://mlsanity.com/paper/2012.05738/) (2020)
- [Abstraction based Output Range Analysis for Neural Networks](https://mlsanity.com/paper/2007.09527/) (2020)
- [Trading Complexity for Sparsity in Random Forest Explanations](https://mlsanity.com/paper/2108.05276/) (2021)
- [Towards Better Understanding Attribution Methods](https://mlsanity.com/paper/2205.10435/) (2022)
- [Modular Semantics and Characteristics for Bipolar Weighted Argumentation Graphs](https://mlsanity.com/paper/1807.06685/) (2018)
- [Optimizing for Interpretability in Deep Neural Networks with Tree Regularization](https://mlsanity.com/paper/1908.05254/) (2019)
- [Weighted defeasible knowledge bases and a multipreference semantics for a deep neural network model](https://mlsanity.com/paper/2012.13421/) (2020)
- [Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects](https://mlsanity.com/paper/2301.07037/) (2023)

## Built on by (most cited first, 18 of 18)

- [Contestable AI needs Computational Argumentation](https://mlsanity.com/paper/2405.10729/) (2024)
- [Contribution Functions for Quantitative Bipolar Argumentation Graphs: A Principle-based Analysis](https://mlsanity.com/paper/2401.08879/) (2024)
- [Intrinsic User-Centric Interpretability through Global Mixture of Experts](https://mlsanity.com/paper/2402.02933/) (2024)
- [ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]](https://mlsanity.com/paper/2311.15438/) (2023)
- [Explaining Arguments' Strength: Unveiling the Role of Attacks and Supports (Technical Report)](https://mlsanity.com/paper/2404.14304/) (2024)
- [CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)](https://mlsanity.com/paper/2407.08497/) (2024)
- [Neuro-Argumentative Learning with Case-Based Reasoning](https://mlsanity.com/paper/2505.15742/) (2025)
- [On Gradual Semantics for Assumption-Based Argumentation](https://mlsanity.com/paper/2507.10076/) (2025)
- [Latent Debate: A Surrogate Framework for Interpreting LLM Thinking](https://mlsanity.com/paper/2512.01909/) (2025)
- [Hidden Conflicts in Neural Networks and Their Implications for Explainability](https://mlsanity.com/paper/2310.20363/) (2023)
- [Set Contribution Functions for Quantitative Bipolar Argumentation and their Principles](https://mlsanity.com/paper/2509.14963/) (2025)
- [Integrating Symbolic Reasoning into Neural Generative Models for Design Generation](https://mlsanity.com/paper/2310.09383/) (2023)
- [From User Preferences to Base Score Extraction Functions in Gradual Argumentation (with Appendix)](https://mlsanity.com/paper/2602.14674/) (2026)
- [Binary Spiking Neural Networks as Causal Models](https://mlsanity.com/paper/2604.27007/) (2026)
- [Towards an Argumentative Foundation for Evaluative AI](https://mlsanity.com/paper/2608.07473/) (2026)
- [ILLC: Iterative Layer-by-Layer Compression for Enhancing Structural Faithfulness in SpArX](https://mlsanity.com/paper/2503.03693/) (2025)
- [Deep Arguing](https://mlsanity.com/paper/2605.10569/) (2026)
- [A Theory of Post-hoc Debate Judgement](https://mlsanity.com/paper/2608.19002/) (2026)

## Abstract (arXiv)

Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging. Existing approaches often focus on explaining how changing individual inputs affects NNs' outputs. However, an explanation that is consistent with the input-output behaviour of an NN is not necessarily faithful to the actual mechanics thereof. In this paper, we exploit relationships between multi-layer perceptrons (MLPs) and quantitative argumentation frameworks (QAFs) to create argumentative explanations for the mechanics of MLPs. Our SpArX method first sparsifies the MLP while maintaining as much of the original structure as possible. It then translates the sparse MLP into an equivalent QAF to shed light on the underlying decision process of the MLP, producing global and/or local explanations. We demonstrate experimentally that SpArX can give more faithful explanations than existing approaches, while simultaneously providing deeper insights into the actual reasoning process of MLPs.