DBScholar

Back to papers

Missing Value Imputation on Multidimensional Time Series

Summary: DeepMVI is a deep-learning imputation method for multidimensional time series, modeling missing values from temporal signals and cross-series correlations. Robust training with synthetic missing blocks and a temporal-transformer plus learned-embedding kernel regression yields large accuracy gains (often >50%), with slower runtimes but improved downstream analytics. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12615
Venue
VLDB
Year
2021
Pagerank
6.9446462e-05
Overall Rank
4,034 | 72.33%
DOI
10.14778/3476249.3476300

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{bansal_vldb21,
        title = {{Missing Value Imputation on Multidimensional Time Series}},
        author = {Bansal, Parikshit and Deshpande, Prathamesh and Sarawagi, Sunita},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {11},
        pages = {2533--2545},
        doi = {10.14778/3476249.3476300},
        url = {https://doi.org/10.14778/3476249.3476300},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 4 of 4 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers