Database Paper Browser

Back to papers

Inference-friendly Graph Compression for Graph Neural Networks

Summary: IFGC uses an inference-equivalence relation to compress G into a compact G_c that preserves GNN-indistinguishable node pairs, enabling direct or low-overhead inference to accelerate GNNs on large graphs. Three variants—SPGC (direct), (α,r)-compression (tradeoff), and anchored (node-focused)—with provable algorithms and empirical validation. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13953
Venue
VLDB
Year
2025
Pagerank
4.1945683e-05
Overall Rank
10,663 | 25.82%
DOI
10.14778/3746405.3746438

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 3 of 3 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