# Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)

arXiv: https://arxiv.org/abs/2012.05738 · HTML: https://mlsanity.com/paper/2012.05738/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 30 of 39)

- [Interactive Explanations by Conflict Resolution via Argumentative Exchanges](https://mlsanity.com/paper/2303.15022/) (2023)
- [SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]](https://mlsanity.com/paper/2301.09559/) (2023)
- [Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)](https://mlsanity.com/paper/2312.15097/) (2023)
- [Contribution Functions for Quantitative Bipolar Argumentation Graphs: A Principle-based Analysis](https://mlsanity.com/paper/2401.08879/) (2024)
- [Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction](https://mlsanity.com/paper/2408.08226/) (2024)
- [PeerArg: Argumentative Peer Review with LLMs](https://mlsanity.com/paper/2409.16813/) (2024)
- [Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report)](https://mlsanity.com/paper/2307.13582/) (2023)
- [ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]](https://mlsanity.com/paper/2311.15438/) (2023)
- [An ASP approach for reasoning on neural networks under a finitely many-valued semantics for weighted conditional knowledge bases](https://mlsanity.com/paper/2202.01123/) (2022)
- [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)
- [A Methodology for Incompleteness-Tolerant and Modular Gradual Semantics for Argumentative Statement Graphs](https://mlsanity.com/paper/2410.22209/) (2024)
- [Enhancing Conflict Resolution in Language Models via Abstract Argumentation](https://mlsanity.com/paper/2412.16725/) (2024)
- [Free Argumentative Exchanges for Explaining Image Classifiers](https://mlsanity.com/paper/2502.12995/) (2025)
- [Neuro-Argumentative Learning with Case-Based Reasoning](https://mlsanity.com/paper/2505.15742/) (2025)
- [Latent Debate: A Surrogate Framework for Interpreting LLM Thinking](https://mlsanity.com/paper/2512.01909/) (2025)
- [Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement](https://mlsanity.com/paper/2205.11589/) (2022)
- [Argumentatively Coherent Judgmental Forecasting](https://mlsanity.com/paper/2507.23163/) (2025)
- [Strength Change Explanations in Quantitative Argumentation](https://mlsanity.com/paper/2603.00008/) (2026)
- [From Weighted Conditionals of Multilayer Perceptrons to Gradual Argumentation and Back](https://mlsanity.com/paper/2110.03643/) (2021)
- [Argumentative Explanations for Pattern-Based Text Classifiers](https://mlsanity.com/paper/2205.10932/) (2022)
- [Many-valued Argumentation, Conditionals and a Probabilistic Semantics for Gradual Argumentation](https://mlsanity.com/paper/2212.07523/) (2022)
- [Applying Attribution Explanations in Truth-Discovery Quantitative Bipolar Argumentation Frameworks](https://mlsanity.com/paper/2409.05831/) (2024)
- [Argumentation and Machine Learning](https://mlsanity.com/paper/2410.23724/) (2024)
- [Argumentative Ensembling for Robust Recourse under Model Multiplicity](https://mlsanity.com/paper/2506.20260/) (2025)
- [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)
- [A Concept and Argumentation based Interpretable Model in High Risk Domains](https://mlsanity.com/paper/2208.08149/) (2022)
- [Temporal Many-valued Conditional Logics: a Preliminary Report](https://mlsanity.com/paper/2409.09069/) (2024)

## Abstract (arXiv)

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in Formal Argumentation and Machine Learning. We generalize the semantics of feed-forward neural networks to acyclic graphs and study the resulting computational and semantical properties in argumentation graphs. As it turns out, the semantics gives stronger guarantees than existing semantics that have been tailor-made for the argumentation setting. From a machine-learning perspective, the connection does not seem immediately helpful. While it gives intuitive meaning to some feed-forward-neural networks, they remain difficult to understand due to their size and density. However, the connection seems helpful for combining background knowledge in form of sparse argumentation networks with dense neural networks that have been trained for complementary purposes and for learning the parameters of quantitative argumentation frameworks in an end-to-end fashion from data.