ILLC: Iterative Layer-by-Layer Compression for Enhancing Structural Faithfulness in SpArX
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Similar Papers 제목 키워드 기반
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use …
When Does Hillclimbing Fail on Monotone Functions: An entropy compression argument
Hillclimbing is an essential part of any optimization algorithm. An important benchmark for hillclimbing algorithms on pseudo-Boolean functions $f: \{0,1\}^n \to \mathbb{R}$ are (strictly) montone functions, on which a s…
Rank Selection of CP-decomposed Convolutional Layers with Variational Bayesian Matrix Factorization
Convolutional Neural Networks (CNNs) is one of successful method in many areas such as image classification tasks. However, the amount of memory and computational cost needed for CNNs inference obstructs them to run effi…
image-classificationImage ClassificationDistillCSE: Distilled Contrastive Learning for Sentence Embeddings
This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a…
Contrastive LearningKnowledge DistillationSentenceSentence EmbeddingsYOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference
Cross-layer key-value (KV) compression has been found to be effective in efficient inference of large language models (LLMs). Although they reduce the memory consumption of the KV cache, such methods usually introduce no…