Explainable Link Prediction for Emerging Entities in Knowledge Graphs

2020-05-01 · Rajarshi Bhowmik, Gerard de Melo

Despite their large-scale coverage, cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity. Link prediction can alleviate this by inferring a target entity, given a source entity and a query relation. Recent embedding-based approaches operate in an uninterpretable latent semantic vector space of entities and relations, while path-based approaches operate in the symbolic space, making the inference process explainable. However, these approaches typically consider static snapshots of the knowledge graphs, severely restricting their applicability for evolving knowledge graphs with newly emerging entities. To overcome this issue, we propose an inductive representation learning framework that is able to learn representations of previously unseen entities. Our method finds reasoning paths between source and target entities, thereby making the link prediction for unseen entities interpretable and providing support evidence for the inferred link.

📄 PDF Abstract BibTeX arXiv:2005.00637

Code (1)

kingsaint/InductiveExplainableLinkPrediction 공식 구현 pytorch

Tasks

Knowledge Graphs Link Prediction Prediction Representation Learning

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction

2022-09-03 · Yufeng Zhang, Weiqing Wang, Hongzhi Yin, Pengpeng Zhao 외

Inductive link prediction (ILP) is to predict links for unseen entities in emerging knowledge graphs (KGs), considering the evolving nature of KGs. A more challenging scenario is that emerging KGs consist of only unseen …

Contrastive Learning Inductive Link Prediction Knowledge Graphs Link Prediction+2

Explainable Representations for Relation Prediction in Knowledge Graphs

2023-06-22 · Rita T. Sousa, Sara Silva, Catia Pesquita

Knowledge graphs represent real-world entities and their relations in a semantically-rich structure supported by ontologies. Exploring this data with machine learning methods often relies on knowledge graph embeddings, w…

Knowledge Graph Embeddings Knowledge Graphs Prediction Relation+1

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG

2024-10-15 · Jinyoung Kim, Dayoon Ko, Gunhee Kim

In the rapidly evolving landscape of language, resolving new linguistic expressions in continuously updating knowledge bases remains a formidable challenge. This challenge becomes critical in retrieval-augmented generati…

Entity Linking RAG Retrieval Retrieval-augmented Generation

Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings

2022-01-14 · Peng Wang, Xin Xie, Xiaohan Wang, Ningyu Zhang

Previous knowledge graph embedding approaches usually map entities to representations and utilize score functions to predict the target entities, yet they typically struggle to reason rare or emerging unseen entities. In…

Graph Embedding Knowledge Graph Embedding Knowledge Graph Embeddings Link Prediction+1

Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Setting

2022-05-10 · Mingyang Chen, Wen Zhang, Zhen Yao, Xiangnan Chen 외

We study the knowledge extrapolation problem to embed new components (i.e., entities and relations) that come with emerging knowledge graphs (KGs) in the federated setting. In this problem, a model trained on an existing…

Graph Neural Network Knowledge Graphs Link Prediction Meta-Learning