Database Paper Browser

Back to papers

FeatureLTE: Learning to Estimate Feature Importance

Summary: FeatureLTE: first pre-trained, general-purpose FIS estimator for tabular data. Learns meta-models from ~1k datasets to predict feature importance with quality comparable to SOTA, but up to 339x faster and robust/scalable on large inputs. (summarized by gpt-5.4-mini on May 24 2026)

Paper ID
6904
Venue
SIGMOD
Year
2024
Pagerank
4.1945683e-05
Overall Rank
10,963 | 23.74%
DOI
10.1145/3654942

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 1 of 1 cited papers.

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

Rank Cited Paper Year Venue Pagerank
102 The Case for Learned Index Structures 2018 SIGMOD 0.00049545203
Previous Page 1 / 1 Next

Semantically Similar Papers