提出新指标NNRD，量化分子图学习中结构与特征的信息平衡。
A Metric for the Balance of Information in Graph Learning
- 通过独立迭代加噪结构和特征，测量信息退化程度。
- 在多种分子任务中，NNRD与信息损失高度相关，结果直观可信。
- 适合关注数据信息构成的图学习研究者使用。
分子图学习同时利用分子结构和附加特征中的信息。现有研究多倾向于偏向结构或特征以提升性能，但尚不清楚数据集更依赖哪类信息，如何针对性建模仍是开放问题。本文提出噪声-噪声比差异（NNRD），一种定量评估结构与特征间信息丰富度的指标。通过独立对结构和特征进行迭代加噪，保持另一方不变，测量其信息退化情况。在多种分子任务上验证表明，NNRD能有效反映信息损失，结果具有可解释性，优于简单性能聚合。未来工作将拓展至更多数据领域、任务类型，并优化基线模型选择。
原文摘要 · Abstract (English)
Graph learning on molecules makes use of information from both the molecular structure and the features attached to that structure. Much work has been conducted on biasing either towards structure or features, with the aim that bias bolsters performance. Identifying which information source a dataset favours, and therefore how to approach learning that dataset, is an open issue. Here we propose Noise-Noise Ratio Difference (NNRD), a quantitative metric for whether there is more useful information in structure or features. By employing iterative noising on features and structure independently, leaving the other intact, NNRD measures the degradation of information in each. We employ NNRD over a range of molecular tasks, and show that it corresponds well to a loss of information, with intuitive results that are more expressive than simple performance aggregates. Our future work will focus on expanding data domains, tasks and types, as well as refining our choice of baseline model.
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。