Sep 2026· Proceedings of the ACM on Management of Data· 0 citations· 23 references
TL;DR
This work introduces a Graph Neural Network (GNN)-based difficulty estimator that jointly captures topological and semantic aspects of violations, enabling the system to distinguish between cases suitable for automatic repair and those requiring human input.
Abstract
Property graphs are powerful data models, yet they often suffer from inconsistencies caused by violations of integrity constraints. Existing repair strategies are either fully automated—struggling with ambiguous cases that require domain expertise—or human-driven, which lack scalability and overlook budget and user heterogeneity. In this work, we propose a novel approach to property graph repair that integrates automatic inference with user expertise. We introduce a Graph Neural Network (GNN)-based difficulty estimator that jointly captures topological and semantic aspects of violations, enabling the system to distinguish between cases suitable for automatic repair and those requiring human input. Building on this, we design a budgeted, difficulty- and user-aware assignment algorithm that allocates violations to users based on their expertise and capacity while maximizing expected repair quality under resource constraints. We prove the NP-hardness of the problem and provide a Lagrangian relaxation. Extensive experiments demonstrate that our approach significantly improves repair accuracy compared to baselines and substantially reduces the number of involved users compared to both other interactive approaches.
This work proposes to amortize the graph matching (node alignment) problem and showcases the efficiency of this approach on toy and real world SGP problems of increasing complexity including a novel Mass-spectra to Scaffold task that is introduced.
F. Méndez, Paul Krzakala, Gabriel Melo et al.· arXiv.org· 0 citations
The proposed Selective Hypergraph Refinement (SHR) generates candidate residual directions from the hypergraph and evaluates their reliability using graph structure, node attributes, and matched-null evidence, and shows that whether a node changes cluster is jointly governed by its native assignment gap and the directi...
The Dual-GNN Multilevel Coarsening framework uses learning to guide multilevel graph coarsening while retaining combinatorial search for final decision making and achieves the best mean solution quality among all evaluated methods.
Mosaic is presented, a training-free framework that formulates GraphRAG retrieval as a per-query control problem that converts query-specific evidence requirements into a bounded policy over seed selection, graph traversal, stopping, and evidence selection while the corpus graph, indexes, scoring functions, grounding p...
Eunkyeong Lee, Kyeong-Jin Oh, Jinwon Kim et al.· 0 citations
FlowNeg is introduced, a context-conditioned hierarchical generative flow network that amortizes reward-proportional sampling without normalizing a composite reward over the entity set: given a positive triple and corruption side, it selects a type, then an entity.
This paper systematically evaluates the overall performance of representative CS approaches, investigates the impact of intrinsic properties of ground-truth communities, and analyzes the approaches' generalizability within a unified experimental framework to advocate generalizability as a pivotal direction for future r...
Yu-Han Zhou, Zheng Wu, Qing Liu et al.· Proceedings of the ACM on Ma...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.