Deep Sparse Latent Feature Models for Knowledge Graph Completion
- URL: http://arxiv.org/abs/2411.15694v1
- Date: Sun, 24 Nov 2024 03:17:37 GMT
- Title: Deep Sparse Latent Feature Models for Knowledge Graph Completion
- Authors: Haotian Li, Rui Zhang, Lingzhi Wang, Bin Yu, Youwei Wang, Yuliang Wei, Kai Wang, Richard Yi Da Xu, Bailing Wang,
- Abstract summary: In this paper, we introduce a novel framework of sparse latent feature models for knowledge graphs.
Our approach not only effectively completes missing triples but also provides clear interpretability of the latent structures.
Our method significantly improves performance by revealing latent communities and producing interpretable representations.
- Score: 24.342670268545085
- License:
- Abstract: 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.
Related papers
- Towards Graph Foundation Models: The Perspective of Zero-shot Reasoning on Knowledge Graphs [14.392577069212292]
We introduce SCORE, a unified graph reasoning framework that effectively generalizes diverse graph tasks using zero-shot learning.
We evaluate SCORE using 38 diverse graph datasets, covering node-level, link-level, and graph-level tasks across multiple domains.
arXiv Detail & Related papers (2024-10-16T14:26:08Z) - Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting [50.181824673039436]
We propose a Graph Structure Self-Contrasting (GSSC) framework that learns graph structural information without message passing.
The proposed framework is based purely on Multi-Layer Perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge.
It first applies structural sparsification to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting in the sparsified neighborhood to learn robust node representations.
arXiv Detail & Related papers (2024-09-09T12:56:02Z) - A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
We introduce a feature-centric pretraining perspective by treating graph structure as a prior.
Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks.
GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
arXiv Detail & Related papers (2024-06-19T22:30:08Z) - G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning [8.02547453169677]
We propose a novel Graph-based Structure-Aware Prompt Learning Model for commonsense reasoning, named G-SAP.
In particular, an evidence graph is constructed by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and Cambridge Dictionary.
The results reveal a significant advancement over the existing models, especially, with 6.12% improvement over the SoTA LM+GNNs model on the OpenbookQA dataset.
arXiv Detail & Related papers (2024-05-09T08:28:12Z) - Multi-perspective Improvement of Knowledge Graph Completion with Large
Language Models [95.31941227776711]
We propose MPIKGC to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs)
We conducted extensive evaluation of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.
arXiv Detail & Related papers (2024-03-04T12:16:15Z) - Contextualization Distillation from Large Language Model for Knowledge
Graph Completion [51.126166442122546]
We introduce the Contextualization Distillation strategy, a plug-in-and-play approach compatible with both discriminative and generative KGC frameworks.
Our method begins by instructing large language models to transform compact, structural triplets into context-rich segments.
Comprehensive evaluations across diverse datasets and KGC techniques highlight the efficacy and adaptability of our approach.
arXiv Detail & Related papers (2024-01-28T08:56:49Z) - Path-based Explanation for Knowledge Graph Completion [17.541247786437484]
Proper explanations for the results of GNN-based Knowledge Graph Completion models increase model transparency.
Existing practices for explaining KGC tasks rely on instance/subgraph-based approaches.
We propose Power-Link, the first path-based KGC explainer that explores GNN-based models.
arXiv Detail & Related papers (2024-01-04T14:19:37Z) - Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph
Construction [57.854498238624366]
We propose a retrieval-augmented approach, which retrieves schema-aware Reference As Prompt (RAP) for data-efficient knowledge graph construction.
RAP can dynamically leverage schema and knowledge inherited from human-annotated and weak-supervised data as a prompt for each sample.
arXiv Detail & Related papers (2022-10-19T16:40:28Z) - Modeling Multi-Granularity Hierarchical Features for Relation Extraction [26.852869800344813]
We propose a novel method to extract multi-granularity features based solely on the original input sentences.
We show that effective structured features can be attained even without external knowledge.
arXiv Detail & Related papers (2022-04-09T09:44:05Z) - A Dependency Syntactic Knowledge Augmented Interactive Architecture for
End-to-End Aspect-based Sentiment Analysis [73.74885246830611]
We propose a novel dependency syntactic knowledge augmented interactive architecture with multi-task learning for end-to-end ABSA.
This model is capable of fully exploiting the syntactic knowledge (dependency relations and types) by leveraging a well-designed Dependency Relation Embedded Graph Convolutional Network (DreGcn)
Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2020-04-04T14:59:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.