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
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.
Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity
Department of Computer Science, Iowa State University(计算机科学系,爱荷华州立大学);Department of Civil, Construction & Environmental Engineering, Iowa State University(土木、建设与环境工程系,爱荷华州立大学)
Learning Policy Representations for Steerable Behavior Synthesis
Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA(宾夕法尼亚大学电气与系统工程系);Department of Signal Theory and Communications, King Juan Carlos University, Madrid, Spain(胡安 Carlos大学信号理论与通信系)
Institute of Zoology, Chinese Academy of Sciences(中国科学院动物研究所);Institute for Stem Cell and Regeneration, Chinese Academy of Sciences(中国科学院干细胞与再生医学研究院);Beijing Institute for Stem Cell and Regenerative Medicine(北京干细胞与再生医学研究院);University of Chinese Academy of Sciences(中国科学院大学);School of Electronic and Information Engineering, Hebei University of Technology(河北工业大学电子与信息工程学院)
University of California San Diego(加利福尼亚大学圣迭戈分校);Georgia Institute of Technology(佐治亚理工学院);University of California Riverside(加利福尼亚大学河滨分校);San Diego State University(圣迭戈州立大学)
The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics
Bielefeld University(比勒菲尔德大学);Tokyo Institute of Technology(东京技术大学);Simplex, Astera Institute(Simplex,Astera研究所);Honda Research Institute EU(本田欧洲研究院);Cold Spring Harbor Laboratory(冷泉港实验室)
AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations
University of Konstanz(康斯坦茨大学)
本文介绍了注意隐式表示网络(AIR-Nets),这是一种简单但高效的点云三维重建架构。由于以局部和模块化方式表示3D形状可以提高泛化和重建质量,因此AIR-Nets将输入点云编码为一组锚定在3D空间中的局部潜在向量,这些向量局部描述对象的几何形状,以及全局潜在描述,从而实现全局一致性。我们的模型是第一个无网格的,基于编码器的方法,局部描述了一个隐式函数。来自[Zhao et al. 2020]的向量注意力机制作为主要的点云处理模块,并允许排列不变性和平移等变性。当用3D坐标查询时,我们的解码器从全局和附近的局部隐向量中收集信息,以预测占用值。ShapeNet数据集上的实验表明,AIR-Nets的性能明显优于以前最先进的基于编码器的隐式形状学习方法,尤其是在稀疏设置中占主导地位。此外,我们的模型在zero-shot设置中很好地推广到FAUST数据集。最后,由于AIR-Nets使用稀疏的潜在表示并遵循简单的操作方案,因此该模型为未来的工作提供了几个现有的途径。我们的代码可在https://github.com/SimonGiebenhain/AIR-Nets上获得。
Discovering and decoding latent mean-field structure with variational autoencoders
Department of Physics and the James Franck Institute, University of Chicago(芝加哥大学物理系及詹姆斯·弗兰克研究所);CuspAI;AMLab, University of Amsterdam(阿姆斯特丹大学AMLab);Leinweber Institute for Theoretical Physics(莱因韦伯理论物理研究所)