Papers › Learning Constrained Structured Spaces with Application to Multi-Graph Matching

Learning Constrained Structured Spaces with Application to Multi-Graph Matching

3 May 2022Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022 5archive 2025-07-28

Hedda Cohen Indelman, Tamir Hazan

Multi-graph matching is a prominent structured prediction task, in which the predicted label is constrained to the space of cycle-consistent matchings. While direct loss minimization is an effective method for learning predictors over structured label spaces, it cannot be applied efficiently to the problem at hand, since executing a specialized solver across sets of matching predictions is computationally prohibitive. Moreover, there’s no supervision on the ground-truth matchings over cycle-consistent prediction sets. Our key insight is to strictly enforce the matching constraints in pairwise matching predictions and softly enforce the cycle-consistency constraints by casting them as weighted loss terms, such that the severity of inconsistency with global predictions is tuned by a penalty parameter. Inspired by the classic penalty method, we prove that our method theoretically recovers the optimal multi-graph matching constrained solution. Our method's advantages are brought to light in experimental results on the popular keypoint matching task on the Pascal VOC and the Willow ObjectClass datasets.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph MatchingStructured Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Matching PASCAL VOC Direct-2HGM F1 score 0.601 #7 of 31 Archive leaderboard report
Graph Matching PASCAL VOC Direct-2GM F1 score 0.597 #9 of 31 Archive leaderboard report
Graph Matching PASCAL VOC Direct-MGM F1 score 0.575 #11 of 31 Archive leaderboard report
Graph Matching Willow Object Class Direct-MGM matching accuracy 0.987 #5 of 23 Archive leaderboard report
Graph Matching Willow Object Class Direct-2HGM matching accuracy 0.981 #7 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections