paper-with-me

Papers

Deep Sparse Latent Feature Models for Knowledge Graph Completion

2024-11-24 · Haotian Li, Rui Zhang, Lingzhi Wang, Bin Yu, Youwei Wang, Yuliang Wei, Kai Wang, Richard Yi Da Xu, Bailing Wang

Recent progress in knowledge graph completion (KGC) has focused on text-based approaches to address the challenges of large-scale knowledge graphs (KGs). Despite their achievements, these methods often overlook the intricate interconnections between entities, a key aspect of the underlying topological structure of a KG. Stochastic blockmodels (SBMs), particularly the latent feature relational model (LFRM), offer robust probabilistic frameworks that can dynamically capture latent community structures and enhance link prediction. In this paper, we introduce a novel framework of sparse latent feature models for KGC, optimized through a deep variational autoencoder (VAE). Our approach not only effectively completes missing triples but also provides clear interpretability of the latent structures, leveraging textual information. Comprehensive experiments on the WN18RR, FB15k-237, and Wikidata5M datasets show that our method significantly improves performance by revealing latent communities and producing interpretable representations.

📄 PDF Abstract BibTeX arXiv:2411.15694

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graph CompletionKnowledge GraphsLink Prediction

Similar Papers 제목 키워드 기반

Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread

2025-11-15 · Rosario Napoli, Gabriele Morabito, Antonio Celesti, Massimo Villari 외 arxiv

The rise of graph-structured data has driven major advances in Graph Machine Learning (GML), where graph embeddings (GEs) map features from Knowledge Graphs (KGs) into vector spaces, enabling tasks like node classificati…

Node ClassificationKnowledge GraphsLink Prediction

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

2020-10-05 · EMNLP 2020 11 · Xin Lv, Xu Han, Lei Hou, Juanzi Li 외

Multi-hop reasoning has been widely studied in recent years to seek an effective and interpretable method for knowledge graph (KG) completion. Most previous reasoning methods are designed for dense KGs with enough paths …

KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion

2022-08-16 · Zhaoxuan Tan, Zilong Chen, Shangbin Feng, Qingyue Zhang 외

Knowledge Graph Embeddings (KGE) aim to map entities and relations to low dimensional spaces and have become the \textit{de-facto} standard for knowledge graph completion. Most existing KGE methods suffer from the sparsi…

Contrastive LearningKnowledge Graph CompletionKnowledge Graph EmbeddingsKnowledge Graphs

Exploring & Exploiting High-Order Graph Structure for Sparse Knowledge Graph Completion

2023-06-29 · Tao He, Ming Liu, Yixin Cao, Zekun Wang 외

Sparse knowledge graph (KG) scenarios pose a challenge for previous Knowledge Graph Completion (KGC) methods, that is, the completion performance decreases rapidly with the increase of graph sparsity. This problem is als…

Knowledge Graph CompletionLogical Reasoning

DSparsE: Dynamic Sparse Embedding for Knowledge Graph Completion

2024-09-22 · Chuhong Yang, Bin Li, Nan Wu

Addressing the incompleteness problem in knowledge graph remains a significant challenge. Current knowledge graph completion methods have their limitations. For example, ComDensE is prone to overfitting and suffers from …

DecoderKnowledge Graph CompletionRelation