Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

2023-01-04 · Zhixiang Su, Di Wang, Chunyan Miao, Lizhen Cui

Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions. In this paper, we introduce the concepts of relation path coverage and relation path confidence to filter out unreliable paths prior to model training to elevate the model performance. Moreover, we propose Knowledge Reasoning Sentence Transformer (KRST) to predict inductive relations in KGs. KRST is designed to encode the extracted reliable paths in KGs, allowing us to properly cluster paths and provide multi-aspect explanations. We conduct extensive experiments on three real-world datasets. The experimental results show that compared to SOTA models, KRST achieves the best performance in most transductive and inductive test cases (4 of 6), and in 11 of 12 few-shot test cases.

📄 PDF Abstract BibTeX arXiv:2301.01664

Code (1)

zhixiangsu/krst 공식 구현 pytorch

Tasks

Inductive Relation PredictionKnowledge Graphs PredictionRelationRelation PredictionSentence

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Test 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Adam 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Inductive Relation Prediction by BERT

2021-03-12 · Hanwen Zha, Zhiyu Chen, Xifeng Yan

Relation prediction in knowledge graphs is dominated by embedding based methods which mainly focus on the transductive setting. Unfortunately, they are not able to handle inductive learning where unseen entities and rela…

Few-Shot Learning Inductive Learning Inductive Relation Prediction Knowledge Graphs+6

Inductive Relation Prediction Using Analogy Subgraph Embeddings

2021-09-29 · ICLR 2022 4 · Jiarui Jin, Yangkun Wang, Kounianhua Du, Weinan Zhang 외

Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i.e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the rel…

Inductive Bias Inductive Relation Prediction Knowledge Graph Completion 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

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

2019-03-09 · Weizhi Ma, Min Zhang, Yue Cao, Woojeong 외

Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation performance. However, these methods hav…

Explainable Recommendation Knowledge Graphs Recommendation Systems

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

2023-12-21 · Zhixiang Su, Di Wang, Chunyan Miao, Lizhen Cui

Aiming to accurately predict missing edges representing relations between entities, which are pervasive in real-world Knowledge Graphs (KGs), relation prediction plays a critical role in enhancing the comprehensiveness a…

Inductive Relation Prediction Knowledge Graphs Prediction Relation+4