Incomplete Data Imputation

Follow this topic Ask about this topic

Momentum

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

Jul 13Week of Sep 28

Latest papers 48

All topics

Observation-Aligned Mask Priors for Learning Physical Fields from Authentic Occlusions
May 16, 2026Chiyuan Ma, Zihan Zhou, Tianshu YuIncomplete Data Imputation Masked Image Modeling
School of Data Science, The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory
Federated Imputation under Heterogeneous Feature Spaces
May 15, 2026Imane Hocine, Chaimaa Medjadji, Sylvain Kubler +2Incomplete Data Imputation Federated Learning
SnT, University of Luxembourg, Luxembourg · FSTM/DCS, University of Luxembourg, Luxembourg
Order-Agnostic Autoregressive Modelling with Missing Data
May 7, 2026Ignacio Peis, Pablo M. Olmos, Jes FrellsenIncomplete Data Imputation Learning with Missing Data
Technical University of Denmark & Pioneer Centre for AI · Universidad Carlos III de Madrid
Data Language Models: A New Foundation Model Class for Tabular Data
May 7, 2026Eda Erol, Giuliano Pezzoli, Ozer Cem KelahmetTabular Foundation Models Incomplete Data Imputation
SchemaLabs
Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
May 6, 2026Olivia Jullian Parra, Sara Zoccheddu, David Catalan Cerezo +7Causal Effect Estimation Normalizing Flows
Department of Mathematical Modeling and Machine Learning University of Zürich Winterthurerstrasse 190, Zürich 8057 · Department of Mathematics ETH Zürich Rämistrasse 101, Zürich 8092 · Epidemiology, Biostatistics & Prevention Institute (EBPI), University of Zürich Hirschengraben 84, Zürich 8001 +2
PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
May 6, 2026Thomas S. Robinson, Ranjit LallIncomplete Data Imputation Causal Discovery
Department of Methodology London School of Economics and Political Science London, UK · Department of Politics and International Relations University of OxfordMay Oxford, UK
Predicting missing values: A good idea?
May 5, 2026Stef van BuurenIncomplete Data Imputation
TNO Netherlands Organization for Applied Scientific Research, Leiden · Dept. of Methodology & Statistics, University of Utrecht
HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation
May 4, 2026Fengming Zhang, Wenjie Du, Huan Zhang +2Time Series Imputation Representation Learning
Center for Energy and Environmental Policy Research, Beijing Institute of Technology, Beijing 100081, China · School of Management, Beijing Institute of Technology, Beijing 100081, China · Beijing Lab for System Engineering of Carbon Neutrality, Beijing 100081, China +1
Missingness-aware Data Imputation via AI-powered Bayesian Generative Modeling
May 3, 2026Qiao LiuIncomplete Data Imputation Uncertainty Quantification
Department of Biostatistics Yale University
SPLICE: Latent Diffusion over JEPA Embeddings for Conformal Time-Series Inpainting
Apr 30, 2026Arnaud ZinflouTime Series Imputation Incomplete Data Imputation
Hydro-Québec Research Institute Canada
End-to-End Learning for Partially-Observed Time Series with PyPOTS
Apr 27, 2026Wenjie Du, Yiyuan Yang, Tianxiang Zhan +1Irregular Time-Series Modeling Time Series Imputation
PyPOTS Research · PyPOTS Research & Univ. of Oxford · Squirrel Ai Learning
Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning
Apr 25, 2026Wugeng Zheng, Ziwen Kan, Katie Wang +2Multimodal Federated Learning Time Series Imputation
University of Central Florida · Independent Researcher
Physics-Conditioned Synthesis of Internal Ice-Layer Thickness for Incomplete Layer Traces
Apr 22, 2026Zesheng Liu, Maryam RahnemoonfarIncomplete Data Imputation Remote Sensing
Department of Computer Science and Engineering Lehigh University Bethlehem, USA
Modeling Information Blackouts in Missing Not-At-Random Time Series Data
Jan 4, 2026Aman Sunesh, Allan Ma, Siddarth NilolTime Series Imputation Incomplete Data Imputation
New York University
FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
Dec 17, 2025Runze Li, Hanchen Wang, Wenjie Zhang +4Time Series Imputation Incomplete Data Imputation
University of New South Wales, Australia · University of Technology Sydney, Australia · The Chinese University of Hong Kong, Shenzhen, China
HAGI++: Head-Assisted Gaze Imputation and Generation
Nov 4, 2025Chuhan Jiao, Zhiming Hu, Andreas BullingGaze Estimation Time Series Imputation
University of Stuttgart, Germany · The Hong Kong University of Science and Technology (Guangzhou), China
Temporal Variational Implicit Neural Representations
Jun 2, 2025Batuhan Koyuncu, Rachael DeVries, Ole Winther +1Irregular Time-Series Modeling Multivariate Time Series Forecasting
Department of Computer Science, Saarland University · Department of Biology, University of Copenhagen · Novo Nordisk A/S +1
SafeImpute: Reliable Clinical Data Imputation via Conformal Selection
Date pendingXinrui He, Mengting Ai, Junting Wang +2Time Series Imputation Incomplete Data Imputation
University of Illinois Urbana-Champaign Champaign, IL, USA · Mayo Clinic Scottsdale, AZ, USA

May 16, 2026, cs.CVJ/K move · Enter open · S save

Observation-Aligned Mask Priors for Learning Physical Fields from Authentic Occlusions

Chiyuan Ma, Zihan Zhou, Tianshu Yu

School of Data Science, The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory

Incomplete Data Imputation Masked Image Modeling

Open paper AskPDF arXiv

Learning physical fields directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and often missing not at random, whereas existing methods typically rely on heuristic masking rules or predefined mask distributions. We propose Observation-Aligned Mask Priors, a framework that learns the distribution of authentic observation masks and uses it to construct context-query partitions for training from incomplete data. Specifically, we pretrain a Bayesian Flow Network (BFN) on binary observation masks to capture real occlusion topologies, then guide BFN sampling with a globally normalized cross-entropy objective to generate sample-specific masks aligned with each sparse observation. The intersection between the guided mask and the observed mask defines the context, and the remaining observed entries become query targets for a diffusion-based reconstruction model. We show that this intersection-based partitioning gives every valid observed dimension a strictly positive probability of being queried, preventing zero-query dead zones and local generative collapse. Experiments on three real-world oceanographic datasets with authentic satellite occlusions, across resolutions up to 256

\times

256, show consistent improvements over strong diffusion baselines in MSE and PSNR. These results demonstrate that learning mask priors from authentic occlusions is an effective alternative to heuristic masking for learning from incomplete physical observations without access to fully observed fields.

Momentum

Related topics

Latest papers 48