# ILLC: Iterative Layer-by-Layer Compression for Enhancing Structural Faithfulness in SpArX

arXiv: https://arxiv.org/abs/2503.03693 · HTML: https://mlsanity.com/paper/2503.03693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Argumentative XAI: A Survey](https://mlsanity.com/paper/2105.11266/) (2021)
- [Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)](https://mlsanity.com/paper/2012.05738/) (2020)
- [SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]](https://mlsanity.com/paper/2301.09559/) (2023)
- [ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]](https://mlsanity.com/paper/2311.15438/) (2023)

## Abstract (arXiv)

In the field of Explainable Artificial Intelligence (XAI), argumentative XAI approaches have been proposed to represent the internal reasoning process of deep neural networks in a more transparent way by interpreting hidden nodes as arguements. However, as the number of layers increases, existing compression methods simplify all layers at once, which lead to high accumulative information loss. To compensate for this, we propose an iterative layer-by-layer compression technique in which each layer is compressed separately and the reduction error in the next layer is immediately compensated for, thereby improving the overall input-output and structural fidelity of the model. Experiments on the Breast Cancer Diagnosis dataset show that, compared to traditional compression, the method reduces input-output and structural unfaithfulness, and maintains a more consistent attack-support relationship in the Argumentative Explanation scheme. This is significant because it provides a new way to make complex MLP models more compact while still conveying their internal inference logic without distortion.