Database Paper Browser

Back to papers

On the Parameterized Complexity of Learning First-Order Logic

Summary: Establishes parameterized complexity bounds for learning first-order queries: proves learning is at least as hard as FO model-checking, yielding AW[*]-hardness on general structures. Gives an FPT agnostic PAC algorithm for FO learning over nowhere-dense (sparse) data. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
1845
Venue
PODS
Year
2022
Pagerank
4.1945683e-05
Overall Rank
11,323 | 21.23%
DOI
10.1145/3517804.3524151

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 2 of 2 cited papers.

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

Rank Cited Paper Year Venue Pagerank
2,124 Characterizing Schema Mappings via Data Examples 2010 PODS 9.4912951e-05
2,750 Learning and Verifying Quantified Boolean Queries by Example 2013 PODS 8.176296e-05
Previous Page 1 / 1 Next

Semantically Similar Papers