One Pass for All: A Discrete Diffusion Model for Knowledge Graph Triple Set Prediction

TL;DR

This paper introduces DiffTSP, a discrete diffusion model that predicts missing triples in knowledge graphs in a single pass, capturing dependencies among triples and achieving state-of-the-art results.

Contribution

The novel DiffTSP model applies a discrete diffusion process to knowledge graph completion, enabling one-pass generation of consistent triple sets.

Findings

Achieves state-of-the-art performance on three datasets.

Generates complete triple sets in a single pass.

Ensures dependency modeling among predicted triples.

Abstract

Knowledge Graphs (KGs) are composed of triples, and the goal of Knowledge Graph Completion (KGC) is to infer the missing factual triples. Traditional KGC tasks predict missing elements in a triple given one or two of its elements. As a more realistic task, the Triple Set Prediction (TSP) task aims to infer the set of missing triples conditioned only on the observed knowledge graph, without assuming any partial information about the missing triples. Existing TSP methods predict the set of missing triples in a triple-by-triple manner, falling short in capturing the dependencies among the predicted triples to ensure consistency. To address this issue, we propose a novel discrete diffusion model termed DiffTSP that treats TSP as a generative task. DiffTSP progressively adds noise to the KG through a discrete diffusion process, achieved by masking relational edges. The reverse process then gradually recovers the complete KG conditioned on the incomplete graph. To this end, we design a structure-aware denoising network that integrates a relational context encoder with a relational graph diffusion transformer for knowledge graph generation. DiffTSP can generate the complete set of triples in a one-pass manner while ensuring the dependencies among the predicted triples. Our approach achieves state-of-the-art performance on three public datasets. Code: https://github.com/ADMIS-TONGJI/DiffTSP.