Hypergraph Learning

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 39

All topics

Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement
May 17, 2026Keshu Wu, Sixu Li, Zihao Li +3Graph Structure Learning Incomplete Data Imputation
Texas A&M University · University of Wisconsin-Madison
HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations
May 16, 2026Xinyi Hong, Shuntuo Xu, Zhou YuGenerative Modeling Hypergraph Learning
School of Statistics East China Normal University
Hypergraph Pattern Machine: Compositional Tokenization for Higher-Order Interactions
May 15, 2026Kyrie Zhao, Zehong Wang, Tianyi Ma +5Feature Interaction Modeling Hypergraph Neural Networks
University of Notre Dame · Stanford University · Yale University +2
Hypergraph Generation via Structured Stochastic Diffusion
May 6, 2026Christopher NemethHypergraph Learning Diffusion Models
School of Mathematical Sciences Lancaster University
Hypergraph and Latent ODE Learning for Multimodal Root Cause Localization in Microservices
May 1, 2026Xin Liu, Yuhang He, Sichen Zhao +2Microservice Architecture Root Cause Analysis
Independent Researcher New York, USA · Independent Researcher Chicago, USA · Northeastern University Boston, USA +2
GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning
Apr 19, 2026Kun Wang, Yiming Li, Mingcheng Qu +3Visual Spatial Reasoning Robot Task Planning
Harbin Institute of Technology, Harbin, China · Chongqing Research Institute of HIT, Chongqing, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China
HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning
Apr 17, 2026Yanbin Wei, Chun Kang, Siwei Li +11VLM Evaluation Large Vision-Language Models
1Southern University of Science and Technology · 2Hong Kong University of Science and Technology · 4Beihang University +1
Bridging Cognitive Neuroscience and Graph Intelligence: Hippocampus-Inspired Multi-View Hypergraph Learning for Web Finance Fraud
Jan 16, 2026Rongkun Cui, Nana Zhang, Kun Zhu +1Long-Tail Learning Multi-View Learning
School of Computer Science and Technology, Tongji University Shanghai, China · School of Computer Science and Technology, Donghua University Shanghai, China
DualHNIE: Dual-Channel Hypergraph Learning for Node Importance Estimation in Heterogeneous Knowledge Graphs
Dec 13, 2025Jiawen Chen, Yanyan He, Qi Shao +4Heterogeneous GNNs Knowledge Graphs
Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing 210096, China · Jiangsu Key Laboratory of Networked Collective Intelligence, School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China · State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, University of Chinese Academy of Sciences, Beijing 100190, China +1

May 17, 2026, cs.LGJ/K move · Enter open · S save

Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement

Keshu Wu, Sixu Li, Zihao Li, Zhiwen Fan+2

Texas A&M University · University of Wisconsin-Madison

Graph Structure Learning Incomplete Data Imputation Learning with Missing Data Hypergraph Neural Networks Hypergraph Learning

Open paper AskPDF arXiv

Sensor networks increasingly govern modern infrastructure, yet the data they lose are rarely missing in the uniform-random patterns assumed by standard imputation benchmarks. Loop detectors go offline during calibration, roadside cabinets silence clusters of nearby sensors, and newly installed instruments provide no history. Such failures create structured absences whose values are constrained by higher-order relations among groups of sensors, not merely by pairwise proximity. Existing low-rank and graph-based methods often miss this collective structure and can fail when missingness becomes coherent. We introduce Multi-Scale Hypergraph Laplacians (MSHL), a two-stage framework for learning higher-order structure from incomplete spatiotemporal observations. The Discovery stage builds a multi-scale hypergraph from complementary topology and residual-correlation evidence, with an observation-only selector that adapts to the supported interaction scale. The Refinement stage adds a small hypergraph-conditioned residual network that is safe by construction: it learns nonlinear corrections where informative residual features exist and defers to the linear estimate where they do not. We prove that MSHL represents group-conservation patterns inaccessible to pairwise graph priors, adapts to the best fixed scale up to a logarithmic factor, transfers this advantage to held-out imputation error, and admits a one-sided refinement guarantee. On two real traffic networks evaluated across scattered cell missingness, contiguous block outages, and whole-sensor blackouts at five rates, MSHL improves over a pairwise-graph baseline whenever higher-order structure is identifiable and otherwise matches it within sampling noise. The results point to a broader principle for reliable infrastructure learning: missing data should be treated not as isolated entries to fill, but as evidence of structure to discover.

Momentum

Related topics

Latest papers 39