Spectral Graph Embedding

Latest papers

16 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Learning Commute-Time-Preserving World Models for Planning
Oct 1, 2026Michael Hauri, Peter Buttaroni, Fabian A. Mikulasch +1Spectral Graph Embedding Representation Learning
Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland · Faculty of Science, University of Basel, Switzerland
Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion
Sep 2, 2026Md Abrar Jahin, Taufikur Rahman Fuad, Jay Pujara +1Spectral Graph Embedding KG Completion
University of Southern California · Islamic University of Technology
Adjacency-Based Spectral Proxy Control of Mobile Communication Agents
Aug 12, 2026Mariana del Castillo, Federico LarrocaSpectral Graph Embedding Multi-Agent Control
Facultad de Ingenier´ıa Universidad de la Rep´ublica Montevideo, Uruguay
Spectral Embeddings of Degree- $α$ Laplacians in Random Dot Product Graphs
Aug 11, 2026John Park, Ning HaoClustering Spectral Clustering
University of Hong Kong · University of Arizona
Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification
Jul 30, 2026V. S. Usatyuk, D. A. Sapozhnikov, S. I. EgorovSpectral Graph Embedding Graph Representation Learning
Department of Computer Engineering, South-West State University (SWSU), Kursk, 305040 Russia · T8 LLC, R&D Department, Information Theory Group, Moscow, 107076 Russia
Group Invariant Spectral Embedding
Jul 9, 2026Yeari Vigder, Paulina Hoyos, David Thong +3Manifold Learning Dimensionality Reduction
Department of Statistics and Operations Research, Tel Aviv University, Tel Aviv, Israel · Department of Mathematics, University of Texas at Austin, Austin, TX, USA · Department of Mathematics, KTH Royal Institute of Technology, Stockholm, Sweden
Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
Jul 8, 2026Jiaqing Xie, Yuxin WangPositional Encoding Spectral Methods
Fudan University
Planar-SfM: Camera Pose Estimation via Homography Graph Embeddings
Jun 30, 2026Gabi Pragier, Matan Karklinsky, David Ungarish +1Spectral Graph Embedding Multi-View Geometry
Amazon Prime Video Live Events
SMGFM: Spectral Multimodal Graph Pretraining for Multimodal-Attributed Graphs
Jun 11, 2026Zhengyu Wu, Xu Wang, Hongchao Qin +4Spectral Graph Embedding Graph Representation Learning
The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers
May 21, 2026Minh Triet Pham, Ian GallagherGraph Embedding Spectral Methods
School of Mathematics and Statistics The University of Melbourne, Australia
Multiscale Euclidean Network Trajectories: Second-Moment Geometry, Attribution, and Change Points
May 6, 2026Haruka Ezoe, Ryohei HisanoSpectral Graph Embedding Dynamic Graph Learning
Graduate School of Information Science and Technology The University of Tokyo · The Canon Institute for Global Studies
Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding
Apr 27, 2026Vasiliy S. Usatyuk, Denis A. Sapozhnikov, Sergey I. EgorovFeature Selection Dimensionality Reduction
R&D Department T8 LLC Moscow, Russia · Department of Computer Science South-West State University Kursk, Russia
Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction
Apr 22, 2026Thinh Nguyen-Cong, Truong-Son Hy, Thang N. DinhGraph Reconstruction Spectral Methods
Department of Computer Science Virginia Commonwealth University Richmond, VA, USA · Department of Computer Science The University of Alabama at Birmingham Birmingham, AL, USA
Uncovering Locally Low-dimensional Structure in Networks by Locally Optimal Spectral Embedding
Mar 12, 2026Hannah Sansford, Nick Whiteley, Patrick Rubin-DelanchySpectral Graph Embedding Graph Embedding
School of Mathematics, University of Bristol, UK · School of Mathematics, University of Edinburgh, UK
Eigenmood Space: Uncertainty-Aware Spectral Graph Analysis of Psychological Patterns in Classical Persian Poetry
Feb 18, 2026Kourosh Shahnazari, Seyed Moein Ayyoubzadeh, Mohammadali KeshtparvarSpectral Graph Embedding Computational Literary Studies
Sharif University of Technology, Tehran, Iran. · Amirkabir University of Technology, Tehran, Iran.
Random Wavelet Features for Graph Kernel Machines
Feb 17, 2026Valentin de Bassompierre, Jean-Charles Delvenne, Laurent JacquesGraph Representation Learning Graph Embedding
INMA/ICTEAM, UCLouvain, Belgium

Oct 1, 2026J/K move · Enter open · S save

Learning Commute-Time-Preserving World Models for Planning

Michael Hauri, Peter Buttaroni, Fabian A. Mikulasch, Friedemann Zenke

Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland · Faculty of Science, University of Basel, Switzerland

Spectral Graph Embedding Representation Learning World Model Learning Latent Dynamics Modeling World Model-Based Planning Model-Based Planning+2

Open paper AskPDF arXiv

World models allow agents to plan in latent space by choosing a sequence of actions that most reduces the distance to a given goal state. Thus, planning can benefit from latent representations whose distances mirror commute-times in the environment. The spectral embedding space of the graph Laplacian provides such a representation, if it obeys a specific eigenvalue-dependent scaling. Unfortunately, instantiating the graph Laplacian is intractable in large, continuous environments. Self-supervised learning offers a natural route to such commute-time-preserving embeddings at scale. However, here we show that existing methods, which commonly encourage isotropic representations to prevent representational collapse, tend to degrade the "correct" eigenvalue-dependent scaling, leading to an inaccurate representation of commute times. To address this problem, we introduce Commute-Time-Preserving World Models (CTWMs), combining a latent displacement predictor and a log-determinant regularizer that prevents collapse, which provably recover the correctly scaled Laplacian representation under reversible deterministic dynamics and at the predictor's fixed point. In numerical simulations, CTWM matches or outperforms LeWM, a task-agnostic baseline, on several complex, continuous goal-reaching benchmarks, while using half the parameters.