发表机构
Northeastern University; Lawrence Livermore National Laboratory（东北大学; 劳伦斯利弗莫尔国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出HGA方法，无需配对样本即可实现潜在空间的无监督对齐，在模型拼接等任务中性能可与有监督方法相当。
AI 中文摘要
独立训练的神经网络倾向于用相似的潜在几何编码相同数据，但这些潜在几何无法直接兼容，仅需经某类变换即可近乎一致。现有多数潜在空间对齐方法依赖被称为“锚点”的共享样本对应关系，这留下一个根本问题：代表相似数据的不同潜在空间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，超球面高斯对齐），该方法通过最大化两个潜在空间间的“拟合”几何度量，直接优化二者间的变换。由于HGA由潜在空间的几何驱动而非配对数据，它可在无监督和弱监督场景下运行。在模型拼接或多语言词嵌入对应恢复等任务中，HGA在极少或无监督的情况下，达到了与有监督结果相当的性能。
英文摘要
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.
