Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)
This work offers a new theoretical lens for understanding certain neural networks, potentially aiding researchers in combining background knowledge with trained neural networks and learning parameters for argumentation frameworks.
This paper proposes a novel interpretation of a class of feed-forward neural networks as quantitative argumentation frameworks, bridging Formal Argumentation and Machine Learning. It generalizes neural network semantics to acyclic graphs, demonstrating stronger guarantees than existing argumentation semantics.
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.