analiza aiqbench
This paper applies conditional discrete diffusion to knowledge graph completion. Instead of scoring individual triples, it generates the missing relational structure of a subgraph in one pass. The reported gains are on three public datasets against baselines, and the lower conflict rates are a secondary result. Readers should check how the baselines were tuned and whether the anonymous code reproduces the results.
DiffTSP: A Conditional Discrete Diffusion Model for Knowledge Graph Triple Set Prediction
arXiv:2604.18344v2 Announce Type: replace Abstract: Triple set prediction (TSP) aims to discover missing facts from an incomplete knowledge graph without predefined queries. Existing approaches typically construct the predicted set through triple-level scoring, sometimes preceded by entity pair filtering that can exclude valid missing facts. We propose DiffTSP, a conditional discrete diffusion model that formulates missing fact discovery as conditional subgraph generation. In each subgraph, DiffTSP directly predicts the missing relational structure without a separate entity pair selection stage. The model learns to generate masked target relation states at different corruption levels, with the observed support subgraph retained as conditioning context. Our structure-aware denoising network integrates a Relational Context Encoder, which captures local relational patterns through relation-guided message passing, and a Relational Graph Diffusion Transformer, which models broader structural interactions through relational attention. During generation, partially generated relations can also serve as provisional context for subsequent predictions. Experiments on three public datasets demonstrate improved TSP performance over strong baselines. Additional analyses show lower conflict rates in the predicted triple sets relative to the evaluated baselines. Code: https://anonymous.4open.science/r/DiffTSP-0F92/.
Abstract:Triple set prediction (TSP) aims to discover missing facts from an incomplete knowledge graph without predefined queries. Existing approaches typically construct the predicted set through triple-level scoring, sometimes preceded by entity pair filtering that can exclude valid missing facts. We propose DiffTSP, a conditional discrete diffusion model that formulates missing fact discovery as conditional subgraph generation. In each subgraph, DiffTSP directly predicts the missing relational structure without a separate entity pair selection stage. The model learns to generate masked target relation states at different corruption levels, with the observed support subgraph retained as conditioning context. Our structure-aware denoising network integrates a Relational Context Encoder, which captures local relational patterns through relation-guided message passing, and a Relational Graph Diffusion Transformer, which models broader structural interactions through relational attention. During generation, partially generated relations can also serve as provisional context for subsequent predictions. Experiments on three public datasets demonstrate improved TSP performance over strong baselines. Additional analyses show lower conflict rates in the predicted triple sets relative to the evaluated baselines. Code: this https URL.
Artificial Intelligence (cs.AI)
arXiv:2604.18344 [cs.AI]
(or arXiv:2604.18344v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2604.18344 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 265 cuvinte
Subiecte conexe
Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models
arXiv · 6 iun. 2026
RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion
arXiv · 21 iul. 2026
ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
arXiv · 16 sept. 2026
Your Discrete Graph Diffusion Model is Secretly Memorizing
arXiv · 12 oct. 2026