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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Yisen, Bai, Jiaxin, Huang, Yi, Fu, Xingcheng, Sun, Qingyun, Song, Yangqiu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915789791035392
author Gao, Yisen
Bai, Jiaxin
Huang, Yi
Fu, Xingcheng
Sun, Qingyun
Song, Yangqiu
author_facet Gao, Yisen
Bai, Jiaxin
Huang, Yi
Fu, Xingcheng
Sun, Qingyun
Song, Yangqiu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11462
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
Gao, Yisen
Bai, Jiaxin
Huang, Yi
Fu, Xingcheng
Sun, Qingyun
Song, Yangqiu
Artificial Intelligence
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.
title Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model
topic Artificial Intelligence
url https://arxiv.org/abs/2510.11462