DIM-SUM: Dynamic Imputation for Smart Utility Management
Summary: DIM-SUM trains robust time-series imputers on real, heterogeneous missingness via pattern clustering and adaptive masking, with theoretical guarantees. At billion-reading scale, it matches accuracy using less data and time, and outperforms a large pretrained model.
(summarized by gpt-5.6-luna on Jul 24 2026)
@article{hildebrant_vldb25,
title = {{DIM-SUM: Dynamic Imputation for Smart Utility Management}},
author = {Hildebrant, Ryan and Bhope, Rahul and Mehrotra, Sharad and Tull, Christopher and Venkatasubramanian, Nalini},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {4451--4464},
doi = {10.14778/3749646.3749705},
url = {https://doi.org/10.14778/3749646.3749705},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
Rank
Citing Paper
Year
Venue
Pagerank
PreviousPage 1 / 1Next
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.