Database Paper Browser

Back to papers

DIM-SUM: Dynamic IMputation for Smart Utility Management

Summary: DIM-SUM is a preprocessing framework that learns realistic missing-data distributions via pattern clustering and adaptive masking to train robust imputation models with provable learning guarantees. On >2B infrastructure readings it outperforms large pre-trained models (~2x accuracy) while using less training data and cutting processing and inference time. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
14058
Venue
VLDB
Year
2025
Pagerank
4.1945683e-05
Overall Rank
10,744 | 25.26%
DOI
10.14778/3749646.3749705

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

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.

Previous Page 1 / 1 Next

Semantically Similar Papers