Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model

2025-10-13

AI Summary

This work addresses the challenge of unifying deductive and abductive reasoning in knowledge graphs to enable their synergistic enhancement. To this end, we propose a bidirectional reasoning framework based on masked diffusion models: it jointly masks queries and conclusions to explicitly model their mutual logical dependencies; incorporates a self-reflective denoising mechanism to improve inference robustness; and integrates logic-guided reinforcement learning to support iterative hypothesis generation and validation. The method synergistically combines knowledge graph embedding, noise-contrastive estimation, and diffusion-based generative modeling. Evaluated on multiple standard knowledge graph benchmarks, our framework achieves state-of-the-art performance on both deductive and abductive reasoning tasks—marking the first successful joint modeling and co-improvement of these two fundamental reasoning paradigms within a unified generative framework.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deductive and abductive reasoning are two critical paradigms for analyzing knowledge graphs, enabling applications from financial query answering to scientific discovery. Deductive reasoning on knowledge graphs usually involves retrieving entities that satisfy a complex logical query, while abductive reasoning generates plausible logical hypotheses from observations. Despite their clear synergistic potential, where deduction can validate hypotheses and abduction can uncover deeper logical patterns, existing methods address them in isolation. To bridge this gap, we propose DARK, a unified framework for Deductive and Abductive Reasoning in Knowledge graphs. As a masked diffusion model capable of capturing the bidirectional relationship between queries and conclusions, DARK has two key innovations. First, to better leverage deduction for hypothesis refinement during abductive reasoning, we introduce a self-reflective denoising process that iteratively generates and validates candidate hypotheses against the observed conclusion. Second, to discover richer logical associations, we propose a logic-exploration reinforcement learning approach that simultaneously masks queries and conclusions, enabling the model to explore novel reasoning compositions. Extensive experiments on multiple benchmark knowledge graphs show that DARK achieves state-of-the-art performance on both deductive and abductive reasoning tasks, demonstrating the significant benefits of our unified approach.

Problem

• Unifying deductive and abductive reasoning in knowledge graphs
• Bridging isolated reasoning paradigms through masked diffusion model
• Enabling bidirectional relationship between queries and conclusions

Innovation

• Unified masked diffusion model for bidirectional reasoning
• Self-reflective denoising process refines hypotheses iteratively
• Logic-exploration reinforcement learning masks queries and conclusions