跨模型向量对应关系可通过局部几何一致性恢复
Vector Linking via Cross-Model Local Isometric Consistency
- 利用不同模型在局部距离上的近似保形性，通过种子锚点迭代匹配向量
- 在多种数据集和模型组合上实现高精度链接，即使在低重叠率下仍稳定
- 适合向量数据库融合与跨模型聚类，对异常锚点具有鲁棒性
我们研究向量链接：给定由不同黑盒编码器在部分重叠数据集上生成的两组嵌入云，仅通过向量恢复跨模型对象对应关系。实证与理论上均表明，独立训练的对比编码器表现出局部几何一致性：短程距离近似保持不变（仅缩放），而长程距离因模型特异性畸变而不一致。基于此，我们提出一种基于参考的迭代几何嵌入哈希方法，从少量配对锚点开始恢复向量链接。该方法将每个向量表示为到采样锚点的距离，通过哈希空间匹配提出候选链接，并利用贝塔-伯努利后验在多视角中聚合证据，逐步将高置信链接作为新锚点。在多个基准和模型对上的实验表明，该方法在不同重叠率、种子预算和域外锚点条件下均表现准确且鲁棒，适用于向量数据库集成与跨模型聚类。代码已开源：https://github.com/DBgroup-Edinburgh/VecLinking。
原文摘要 · Abstract (English)
We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model object correspondences using only vectors. Empirically and theoretically, we show that independently trained contrastive encoders exhibit local geometric consistency: short-range distances are approximately preserved up to a scale factor, while long-range distances are not due to model-specific distortion. Building on this, we propose an iterative, reference-based geometric embedding hashing that recovers vector links from a tiny seed set of paired anchors. It represents each vector by distances to sampled paired anchors, proposes candidate links via hash-space matching, and aggregates evidence across views in a Beta-Bernoulli posterior to bootstrap high-confidence links as new anchors. Experiments across multiple benchmarks and embedding model pairs demonstrate accurate and robust linking under varying overlap, seed budgets, and out-of-domain anchors, with applications to vector database integration and cross-model clustering. Code is available at https://github.com/DBgroup-Edinburgh/VecLinking.
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。