Database Paper Browser

Back to papers

TIGER: Training Inductive Graph Neural Network for Large-scale Knowledge Graph Reasoning

Summary: TIGER speeds inductive GNN training for large-scale KG reasoning via streaming subgraph slicing and dynamic caching. Optimal slicing proved NP-hard; SiGMa (two-stage decoupling) achieves high slice reuse and ~3.7× subgraph-extraction speedup on Freebase (86M). (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13472
Venue
VLDB
Year
2024
Pagerank
4.1945683e-05
Overall Rank
11,033 | 23.25%
DOI
10.14778/3675034.3675039

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 12 of 12 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