Toward More Explainable Nonlinear Dimensionality Reduction: A Feature-Driven Interaction Approach

Nonlinear dimensionality reduction (NDR) techniques are widely used to visualize high-dimensional data. However, they often lack explainability, making it challenging for analysts to relate patterns in projections to original high-dimensional features. Existing interactive methods typically separate user interactions from the feature space, treating them primarily as post-hoc explanations rather than integrating them into the exploration process. This separation limits insight generation by restricting users' understanding of how features dynamically influence projections. To address this limitation, we propose a bidirectional interaction method that directly bridges the feature space and the projections. By allowing users to adjust feature weights, our approach enables intuitive exploration of how different features shape the embedding. We also define visual semantics to quantify projection changes, enabling structured pattern discovery through automated query-based interaction. To ensure responsiveness despite the computational complexity of NDR, we employ a neural network to approximate the projection process, enhancing scalability while maintaining accuracy. We evaluated our approach through quantitative analysis, assessing accuracy and scalability. A user study with a comprehensive visual interface and case studies demonstrated its effectiveness in supporting hypothesis generation and exploratory tasks with real-world data. The results confirmed that our approach supports diverse analytical scenarios and enhances users' ability to explore and interpret high-dimensional data through interactive exploration grounded in the feature space.