跳到正文
arXiv cs.AI· Song Young Oh, Nesar Ramachandra, Bin Xia, Ian Foster, Kyle Chard·· 10 小时前AI 评分20

多目标检索如何为异构科学模态搜索帕累托前沿

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

AI 导读

研究对比多模态基础模型与独立训练嵌入经帕累托最优多目标优化融合的晚期融合方案,在星系检索任务上评估恒星形成历史、光谱及两台望远镜多波段观测等异构模态。该方法保留了模态特有的距离结构,可让科学家查看哪些物理信号驱动相似性;在六项测量属性上,其最近邻平均比 FM 嵌入空间 kNN 检索结果接近查询 8%(0.128 对 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