用神经网络自动学习数据排序策略，适配多种评估指标。
Versatile Ordering Network: An Attention-based Neural Network for Ordering Across Scales and Quality Metrics
- 基于注意力机制和强化学习，自适应生成排序方案。
- 在不同指标下表现接近专用求解器，泛化能力强。
- 适合需要灵活排序的可视化、数据分析场景。
排序在可视化应用中被广泛研究，如坐标轴和矩阵重排，因为顺序显著影响数据模式的感知。针对数据模式、感知和美学等质量指标，已有多种优化算法被提出。然而，排序优化问题通常难以求解（如旅行商问题为NP完全），且开发专用算法成本较高。本文提出通用排序网络（VON），可自动学习基于质量指标的排序策略。VON利用质量指标评估自身解，并通过带有贪婪回溯基线的强化学习进行迭代优化，保持指标透明并支持多指标优化。此外，VON采用注意力机制跨尺度收集信息，根据上下文重新定位数据点，从而处理不同分布的数据。我们在多种使用场景和指标下验证了VON的有效性，结果表明其性能可媲美专用求解器。代码已开源：https://github.com/sysuvis/VON。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。