Database Paper Browser

Back to papers

Factorized Graph Representations for Semi-Supervised Learning from Sparse Data

Summary: Factorized graph representations enable distant compatibility estimation for semi-supervised learning on ultra-sparse graphs. Using size-independent graph sketches and algebraic amplification, the estimator runs orders of magnitude faster and achieves accuracy comparable to gold compatibilities, providing a cheap pre-processing step for label propagation. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
5790
Venue
SIGMOD
Year
2020
Pagerank
4.1945683e-05
Overall Rank
11,560 | 19.58%
DOI
10.1145/3318464.3380577

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 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
5,962 Beyond Equi-joins: Ranking, Enumeration and Factorization 2021 VLDB 5.2536266e-05
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.

Rank Cited Paper Year Venue Pagerank
254 Snorkel: Rapid Training Data Creation with Weak Supervision 2018 VLDB 0.00030540555
1,740 A General Framework for Estimating Graphlet Statistics via Random Walk 2017 VLDB 0.0001071792
3,930 ZooBP: Belief Propagation for Heterogeneous Networks 2017 VLDB 6.6209573e-05
6,015 Linearized and Single-Pass Belief Propagation 2015 VLDB 5.2415551e-05
Previous Page 1 / 1 Next

Semantically Similar Papers