GABoost: Graph Alignment Boosting via Local Optimum Escape

Summary: GABoost: a boosting framework for heterogeneous-graph alignment; from an initial alignment, it iteratively escapes local optima to improve matches. It is modular and compatible with any upstream method, yielding ~25% average accuracy gain across 7 methods on 6 real datasets with modest overhead. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6965
Venue: SIGMOD
Year: 2024
Pagerank: 4.4937074e-05
Overall Rank: 8,524 | 40.71%
DOI: 10.1145/3677135

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,692	Fused Gromov-Wasserstein Alignment for Graph Edit Distance Computation and Beyond	2025	VLDB	4.1945683e-05

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
10,945	Efficient High-Quality Clustering for Large Bipartite Graphs	2024	SIGMOD	4.1945683e-05
3,752	Computing Graph Edit Distance via Neural Graph Matching	2023	VLDB	6.7879009e-05
6,441	Efficient Exact Subgraph Matching via GNN-based Path Dominance Embedding	2024	VLDB	5.0603113e-05
11,560	Factorized Graph Representations for Semi-Supervised Learning from Sparse Data	2020	SIGMOD	4.1945683e-05
2,007	Exploiting Vertex Relationships in Speeding up Subgraph Isomorphism over Large Graphs	2015	VLDB	9.8081235e-05
6,839	Boosting Graph Similarity Search through Pre-Computation	2021	SIGMOD	4.9109527e-05
8,908	Deep Active Alignment of Knowledge Graph Entities and Schemata	2023	SIGMOD	4.427232e-05
3,915	A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs	2020	VLDB	6.6332294e-05
6,760	GAIA: Graph Classification Using Evolutionary Computation	2010	SIGMOD	4.9349071e-05
10,487	Graph Edit Distance Estimation: A New Heuristic and A Holistic Evaluation of Learning-based Methods	2025	SIGMOD	4.1945683e-05