Versatile Ordering Network: An Attention-based Neural Network for Ordering Across Scales and Quality Metrics

TL;DR

The paper introduces Versatile Ordering Network (VON), an attention-based neural network that learns to optimize data ordering across various quality metrics using reinforcement learning, addressing complex ordering problems efficiently.

Contribution

VON is a novel neural network that automatically learns ordering strategies for different metrics, leveraging attention and reinforcement learning to handle diverse data distributions.

Findings

VON achieves results comparable to specialized solvers.

VON effectively adapts to different quality metrics.

VON handles data with varying distributions.

Abstract

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.