mlsanityData to 14 Oct 2026

GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation

arXiv 2609.30340 ↗First posted 24 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Air-quality sensor outages often create contiguous missing blocks, where side information useful for isolated missingness may be less reliable. We study a block-specific, GAUDI-aligned conditional diffusion imputer that retains temporal and feature processing, visible-value and mask conditioning, variable identity, and diffusion-step information, while suppressing absolute time-position side embeddings. On ItalyAir (13 variables, length-32 windows, nominal 50% block missingness; three archived seeds), this feature-side configuration achieves RMSE 0.340, versus 0.355 for full context and 0.355 for local CSDI. The experiment isolates a geometry-aware conditioning effect under block missingness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

17 of 21 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  5. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  6. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  7. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  8. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  9. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  10. 2024TSI-Bench: Benchmarking Time Series Imputationcited by 33
  11. 2026How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Predictioncited by 8
  12. 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learningcited by 7
5 more
  1. 2025Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarioscited by 5
  2. 2026MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Predictioncited by 4
  3. 2025Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safetycited by 2
  4. 2025FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputationcited by 2
  5. 2026Decomposing Firm-Level Crisis Responses from Incomplete Market Signals: Evidence from China's IT Sector During COVID-19cited by 2

Built on by

Not cited yet.