Versatile Ordering Network: An Attention-based Neural Network for Ordering Across Scales and Quality Metrics
This addresses the challenge of developing efficient ordering algorithms for visualization tasks, though it is incremental as it builds on existing reinforcement learning and attention mechanisms.
The paper tackles the problem of ordering data in visualization applications, which is often NP-complete and costly to optimize, by proposing Versatile Ordering Network (VON), an attention-based neural network that automatically learns ordering strategies for various quality metrics, producing results comparable to specialized solvers.
Ordering has been extensively studied in many visualization applications, such as axis and matrix reordering, for the simple reason that the order will greatly impact the perceived pattern of data. Many quality metrics concerning data pattern, perception, and aesthetics are proposed, and respective optimization algorithms are developed. However, the optimization problems related to ordering are often difficult to solve (e.g., TSP is NP-complete), and developing specialized optimization algorithms is costly. In this paper, we propose Versatile Ordering Network (VON), which automatically learns the strategy to order given a quality metric. VON uses the quality metric to evaluate its solutions, and leverages reinforcement learning with a greedy rollout baseline to improve itself. This keeps the metric transparent and allows VON to optimize over different metrics. Additionally, VON uses the attention mechanism to collect information across scales and reposition the data points with respect to the current context. This allows VONs to deal with data points following different distributions. We examine the effectiveness of VON under different usage scenarios and metrics. The results demonstrate that VON can produce comparable results to specialized solvers. The code is available at https://github.com/sysuvis/VON.