共享几何并非共享物理:天文学中柏拉图表示假设的逐层检验
Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy
浏览论文内容
中文总结 AI 辅助
本文检验天文学中柏拉图表示假设,发现几何对齐的表示在科学上不可互换,几何选择阶段不如标签选择,红移迁移为负R^2。
中文摘要 AI 辅助
本文研究了几何对齐的天文表示是否在科学上可互换。我们使用交叉匹配的光学图像、红外图像和光谱,分析了36个预训练模型中每一层的表示。所有139个模型-巡天比较在考虑深度搜索后,在网络中的某处均显示出显著的局部邻域对齐。然而,对齐通常不随网络深度增加而增强,并且对于连续计算块之间的变化可能比对块输出本身更强。我们发现,在每次图像迁移比较中,几何选择的阶段均不如标签选择的阶段;此外,每一对最终的HSC-COSMOS-Web模型都是对齐的,而每次红移迁移的R^2均为负值。因此,模型可以恢复天文物体之间相似的跨巡天几何,而无需恢复此处测试的物理属性的巡天不变线性编码。
英文摘要
In this paper we investigate whether geometrically aligned astronomical representations are also scientifically interchangeable. We analyze every layer's representation from 36 pretrained models using cross-matched optical images, infrared images, and spectra. All 139 analyzed model-survey comparisons show significant local-neighborhood alignment somewhere in the network after accounting for the search over depth. However, alignment does not generally increase with network depth and can be stronger for the changes between consecutive computational blocks than for the block outputs themselves. We find that geometry-selected stages under-perform label-selected stages in every image-transfer comparison; moreover, every final HSC-COSMOS-Web model pair is aligned while every redshift transfer has negative R^2. Models can therefore recover a similar cross-survey geometry among astronomical objects without recovering a survey-invariant linear encoding of the physical properties tested here.
发表机构
- UniverseTBD
- EleutherAI
- INTI International College Penang(英迪国际学院槟城分院)
- Center for Astrophysics, Harvard & Smithsonian(哈佛-史密森尼天体物理中心)
- AstroAI
- Space Telescope Science Institute(空间望远镜科学研究所)
- Johns Hopkins University(约翰斯·霍普金斯大学)
机构由 AI 辅助整理,请以论文原文为准。