arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.22823cs.LG
收藏

基于超网络的网格无关函数数据聚类方法

Hypernetwork-based approach for grid-independent functional data clustering

Department of Computer Science(计算机科学系);University of Central Florida(中央佛罗里达大学)

Anirudh Thatipelli, Ali Siahkoohi

AI总结:

本文提出基于超网络的函数数据聚类方法,通过隐式神经表示实现网格无关的紧凑表示,提升高维数据下对采样分辨率变化的鲁棒性。

摘要:

函数数据聚类旨在将具有相似结构的函数分组,但现有大多数方法隐式地在采样网格上操作,导致聚类分配依赖于分辨率、采样密度或预处理选择,而非底层函数本身。为解决这一限制,我们引入了一种框架,通过自编码架构将离散化的函数观测(在任意分辨率和任意网格上)映射到固定维度的向量空间。编码器是一个超网络,将坐标-值对映射到隐式神经表示(INR)的权重空间,该空间作为解码器。由于INR用极少数参数表示函数,这种设计产生了与采样网格解耦的紧凑表示,同时超网络在数据集中摊销权重预测。随后在该权重空间中使用标准算法进行聚类,使该方法对离散化和聚类方法的选择都无偏见。通过高维设置中的合成和实际实验,我们展示了在采样分辨率变化时具有竞争力的聚类性能,包括对训练期间未见的分辨率的泛化能力。

英文摘要:

Functional data clustering is concerned with grouping functions that share similar structure, yet most existing methods implicitly operate on sampled grids, causing cluster assignments to depend on resolution, sampling density, or preprocessing choices rather than on the underlying functions themselves. To address this limitation, we introduce a framework that maps discretized function observations -- at arbitrary resolution and on arbitrary grids -- into a fixed-dimensional vector space via an auto-encoding architecture. The encoder is a hypernetwork that maps coordinate-value pairs to the weight space of an implicit neural representation (INR), which serves as the decoder. Because INRs represent functions with very few parameters, this design yields compact representations that are decoupled from the sampling grid, while the hypernetwork amortizes weight prediction across the dataset. Clustering is then performed in this weight space using standard algorithms, making the approach agnostic to both the discretization and the choice of clustering method. By means of synthetic and real-world experiments in high-dimensional settings, we demonstrate competitive clustering performance that is robust to changes in sampling resolution -- including generalization to resolutions not seen during training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑