Pith. sign in

REVIEW 2 cited by

Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.13075 v1 pith:2A3GHWJG submitted 2024-05-21 cs.LG

classification cs.LG
keywords timeseriestemporaldiffusionfeaturesgloballocalscore-cdm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multivariant time series (MTS) data are usually incomplete in real scenarios, and imputing the incomplete MTS is practically important to facilitate various time series mining tasks. Recently, diffusion model-based MTS imputation methods have achieved promising results by utilizing CNN or attention mechanisms for temporal feature learning. However, it is hard to adaptively trade off the diverse effects of local and global temporal features by simply combining CNN and attention. To address this issue, we propose a Score-weighted Convolutional Diffusion Model (Score-CDM for short), whose backbone consists of a Score-weighted Convolution Module (SCM) and an Adaptive Reception Module (ARM). SCM adopts a score map to capture the global temporal features in the time domain, while ARM uses a Spectral2Time Window Block (S2TWB) to convolve the local time series data in the spectral domain. Benefiting from the time convolution properties of Fast Fourier Transformation, ARM can adaptively change the receptive field of the score map, and thus effectively balance the local and global temporal features. We conduct extensive evaluations on three real MTS datasets of different domains, and the result verifies the effectiveness of the proposed Score-CDM.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FreshRetailNet-50K: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

    cs.LG 2025-05 conditional novelty 6.0 of 10

    FreshRetailNet-50K is the first open hourly stockout-annotated benchmark for censored fresh-retail demand, and a two-stage impute-then-forecast pipeline reduces bias in 7-day demand forecasts.

  2. STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation

    cs.LG 2025-06 conditional novelty 5.0 of 10

    STAMImputer uses a mixture-of-experts framework with low-rank guided graph attention to impute missing traffic data, reporting small MAE improvements over prior methods on four benchmarks.

Pith tools