无需配对数据，用几何匹配实现不同模型隐空间的自动对齐。
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching
- 基于隐空间球面几何距离优化变换，不依赖成对样本。
- 在无监督/弱监督下达到与有监督方法相当的对齐效果。
- 适用于模型拼接、多语言词向量对齐等场景。
独立训练的神经网络倾向于以相似的隐空间几何结构编码相同数据。尽管这些几何结构不直接兼容，但它们在某些变换类别下几乎相同。现有对齐方法通常依赖共享样本对应（锚点），这引发一个根本问题：不同隐空间中表示相似数据的几何特征是否足以恢复它们之间的对齐？为此，我们提出HGA（Hyperspherical Gaussian Alignment），一种通过最大化隐空间间几何“契合度”来直接优化变换的方法。由于其依赖隐空间几何而非成对数据，HGA可在无监督和弱监督条件下运行。在模型拼接或多语言词嵌入对应恢复等任务中，HGA仅需极少或无需监督即可达到与有监督方法相当的效果。
原文摘要 · Abstract (English)
Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the same up to some class of transformations. While there exists many methods for alignment between different latent spaces, it is typically done using a set of shared sample correspondences, known as anchors. This leaves a fundamental question: are the geometric signatures of different latent spaces representing similar data sufficient to recover an alignment between them? To that end, we introduce HGA (Hyperspherical Gaussian Alignment), a method that directly optimizes a transformation between two latent spaces by maximizing a geometric measure of "fit" between them. Since it is driven by the geometry of the latent spaces rather than paired data, HGA can operate in both an unsupervised and weakly supervised regime. On tasks such as model stitching or multilingual word embedding correspondence recovery, HGA manages to match supervised results with minimal or no supervision.
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。