arXiv cs.AI· Jiaqi Wang, Yisen Gao, Huayang Shi, Junhao Hou, Wengen Li, Jihong Guan, Yichao Zhang, Shuigeng Zhou, Yangqiu Song, Hong Cheng·· 4 小时前AI 评分25
LatentDiff：基于观测锚定的潜在扩散模型从局部补全走向统一生成的三元组集合预测
From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
AI 导读
知识图谱补全研究提出 LatentDiff，一种统一潜在生成框架，将三元组集合预测（TSP）重构为潜在空间图生成。框架先用关系感知残差量化自编码器编码整图，再通过观测锚定的潜在图扩散模型逐步去噪恢复缺失三元组。在三个 benchmark 数据集上，LatentDiff 的 F_tsp 平均超过 SOTA 5.4 个百分点，代码已开源。
正文 · 原文
Abstract:Triple set prediction (TSP) is to recover missing relational triples in a knowledge graph by predicting the triple set instead of isolated links. Existing approaches predominantly rely on the subgraph-based completion paradigm, where the original graph is first partitioned into local subgraphs which are then independently completed. Such a paradigm suffers from fragmented structural reasoning, limited cross subgraph dependency modeling, and missing predictions across subgraphs. This paper proposes LatentDiff, a novel unified latent generative framework for TSP, which reformulates knowledge graph completion as latent space graph generation. LatentDiff first learns a compact latent representation using a relation-aware residual-quantized knowledge graph autoencoder, which encodes the whole graph into relation-aware latent embeddings, quantizes them with chunked residual codebooks, and reconstructs triples through a factorized decoder. On top of this latent space, we introduce an observation-anchored latent graph diffusion model, where the target latent graph representation is perturbed toward the observed latent. The reverse process recovers missing triples through progressive latent denoising. Experiments on three benchmark datasets show that LatentDiff outperforms the SOTA in terms of F_{tsp} by 5.4 percentage points on average. Code: this https URL.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.39114 [cs.LG] |
| (or arXiv:2610.39114v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.39114 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiaqi Wang [view email]
[v1]
Thu, 29 Oct 2026 00:57:38 UTC (4,256 KB)
来源：arXiv cs.AI · arxiv.org