跳到正文
arXiv cs.AI· Song Young Oh, Nesar Ramachandra, Bin Xia, Ian Foster, Kyle Chard·· 1 小时前AI 评分35

基于帕累托前沿的多目标检索:面向异构科学模态的天体物理数据检索方法研究

Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities

AI 导读

一项arXiv论文研究在天文学异构模态数据上用帕累托最优的多目标融合替代多模态基础模型(FM)做检索,在涵盖恒星形成历史、光谱和双望远镜多波段观测的星系检索任务上与FM基线对比。结果显示FM基线嵌入空间邻近性好,而该方法保留了模态-specific距离结构,可追溯驱动相似性的物理信号;在六项实测属性上,其最近邻平均比FM嵌入空间kNN结果更接近查询8%(离散度0.128 vs 0.139)。

正文 · 原文

View PDF HTML (experimental)

Abstract:In cosmology, surveys span different sky regions and wavelength ranges, resulting in uneven modality coverage across observational datasets. Such heterogeneity can be addressed through either multimodal foundation models (FMs), which learn shared embedding spaces, or independently learned modality embeddings combined via late fusion. We investigate whether the latter provides an adaptive alternative to FM-based scientific retrieval. We evaluate this approach on a galaxy retrieval task spanning diverse modalities--history of star formation, spectra of light emitted, and multi-wavelength observations from two telescopes--comparing an FM baseline with separately trained embeddings fused through multi-objective optimization based on Pareto optimality. We find that the FM baseline achieves strong embedding-space proximity, but our method preserves modality-specific distance structure that allows scientists to inspect which physical signals drive similarity. Our method also achieves improved fidelity in raw-data space: across six measured properties, its nearest neighbor is 8% closer to the query on average than that retrieved by kNN in the FM embedding space (spread 0.128 vs. 0.139). These results suggest that multi-objective retrieval can surface astrophysically coherent candidates that single-objective search alone may overlook.
Subjects: Artificial Intelligence (cs.AI); Instrumentation and Methods for Astrophysics (astro-ph.IM)
Cite as: arXiv:2611.23639 [cs.AI]
  (or arXiv:2611.23639v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23639

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Bin Xia [view email]
[v1] Wed, 18 Nov 2026 00:03:22 UTC (2,793 KB)

来源:arXiv cs.AI · arxiv.org