Papers › Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices

Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices

29 Mar 2024Mathematics 2024 3archive 2025-07-28

Pavlo Radiuk, Olexander Barmak, Eduard Manziuk, Iurii Krak

The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability of DL models through visual analytics (VA) and human-in-the-loop (HITL) principles, making these systems more transparent and understandable to end users. In this work, we propose a novel approach that utilizes a transition matrix to interpret results from DL models through more comprehensible machine learning (ML) models. The methodology involves constructing a transition matrix between the feature spaces of DL and ML models as formal and mental models, respectively, improving the explainability for classification tasks. We validated our approach with computational experiments on the MNIST, FNC-1, and Iris datasets using a qualitative and quantitative comparison criterion, that is, how different the results obtained by our approach are from the ground truth of the training and testing samples. The proposed approach significantly enhanced model clarity and understanding in the MNIST dataset, with SSIM and PSNR values of 0.697 and 17.94, respectively, showcasing high-fidelity reconstructions. Moreover, achieving an F1m score of 77.76% and a weighted accuracy of 89.38%, our approach proved its effectiveness in stance detection with the FNC-1 dataset, complemented by its ability to explain key textual nuances. For the Iris dataset, the separating hyperplane constructed based on the proposed approach allowed for enhancing classification accuracy. Overall, using VA, HITL principles, and a transition matrix, our approach significantly improves the explainability of DL models without compromising their performance, marking a step forward in developing more transparent and trustworthy AI systems.

Paper PDF Code

Code

radiukpavlo/transition-matrix-dl officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep Learning Explainable Artificial Intelligence (XAI)Image Generation Interpretability Techniques for Deep Learning Interpretable Machine Learning SSIM Stance Detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Generation	MNIST	Transition Matrix	PSNR	17.94	#15 of 15	Archive leaderboard	report
Image Generation	MNIST	Transition Matrix	SSIM	0.697	#15 of 15	Archive leaderboard	report
Stance Detection	FNC-1	Transition Matrix	F1	77.76	#2 of 2	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Dropout BERT Convolution DCNN Dropout Label Smoothing Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Position-Wise Feed-Forward Layer RoBERTa Softmax Transformer Visual Analytics Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections