arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.11142cs.LG
收藏

秩不是容量:潜在图模型的谱占用

Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models

Human Nature Lab, Yale University(耶鲁大学人类本质实验室);Department of Electrical and Computer Engineering, Yale University(耶鲁大学电气与计算机工程系);Department of Statistics and Data Science, Yale University(耶鲁大学统计与数据科学系);Department of Computer Science, Yale University(耶鲁大学计算机科学系)

Nikolaos Nakis, Panagiotis Promponas, Konstantinos Tsirkas, Katerina Mamali, Eftychia Makri, Leandros Tassiulas, Nicholas A. Christakis

AI总结:

本文提出Spectra方法,通过谱分析替代秩作为分析单位,以更准确衡量模型容量,从而在预测精度与实际维度之间建立可可视化权衡。

摘要:

图表示学习已成为分析网络数据的标准方法,潜在嵌入广泛用于链接预测、社区检测等任务。然而,基本设计选择——潜在维度——仍被视为易碎的超参数,在训练前固定并通过验证性能调整。学习因素只能在旋转和缩放范围内识别,因此名义秩很少与决定模型行为的量一致。我们提出Spectral Prefix Extraction和Capacity-Targeted Representation Analysis(Spectra),通过学习正半定核的谱替代秩作为分析单位,经过迹归一化后,使谱在不同拟合间可比。归一化特征值形成简单集上的分布,其Shannon有效秩同时作为学习容量的总结和可控训练时坐标:单个标量在训练中塑造此实际维度,二分法可目标任何在秩上限内的值。为理论支持,我们展示了实际维度轮廓的局部正则性和单调性。在合作、社交、生物和基础设施网络中,Spectra追踪性能-容量前沿,使预测精度与实际维度之间的权衡可视化。它在强链接预测基线中表现竞争,通过谱前缀提供对同一拟合模型的对齐低容量视图,并在过参数化范围内提供容量的原理性处理。容量因此成为拟合模型的属性,而非训练的超参数。

英文摘要:

Graph representation learning has become a standard approach for analyzing networked data, with latent embeddings widely used for link prediction, community detection, and related tasks. Yet a basic design choice, the latent dimension, is still treated as a brittle hyperparameter, fixed before training and tuned by held-out performance. Learned factors are also identifiable only up to rotation and rescaling, so the nominal rank rarely coincides with the quantity that governs model behavior. We propose Spectral Prefix Extraction and Capacity-Targeted Representation Analysis (Spectra), which replaces rank as the unit of analysis with the spectrum of a learned positive semidefinite kernel, trace-normalized so that spectra are comparable across fits. The normalized eigenvalues form a distribution on the simplex, and their Shannon effective rank acts both as a summary of learned capacity and as a controllable training-time coordinate: a single scalar shapes this realized dimension during training, and bisection targets any desired value within the rank cap. To theoretically support that, we show local regularity and monotonicity of the realized-dimension profile. Across collaboration, social, biological, and infrastructure networks, Spectra traces performance--capacity frontiers that make the trade-off between predictive accuracy and realized dimension visible. It performs competitively with strong link-prediction baselines, yields aligned lower-capacity views of the same fitted model through spectral prefixes, and provides a principled handle on capacity in the overparameterized regime. Capacity thus becomes a property of the fitted model rather than a hyperparameter of the 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。

↑