本文前置知识: BERT(Transformer Encoder). PPKE: Knowledge Representation Learning by Path-based Pre-training本文是论文PPKE: Know
2021-01-18
Argparse和LoggingArgparse和LoggingArgparse和Logging是Python实验中常用的两个模块. 之前没有整理过, 特此整理. ArgparseArgparse是用来解析Python命令行的标准库. 框架大致使用框架如下: impor
2021-01-06
RREA: Relational Reflection Entity Alignment本文前置知识: GNN Relational Reflection Entity Alignment本文是论文Relational Reflection Entity Alignment的阅读笔记和个人理解. 这是我第一次接触关于实
2020-12-30
Realistic Re-evaluation of KGC Methods: An Experimental StudyRealistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study本文是论文Realistic Re-evaluation of Know
2020-12-27
Can We Predict New Facts with Open Knowledge Graph Embeddings?Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction本文是论文Can We Predict N
2020-12-13
Generative Adversarial Zero-Shot Relational Learning for KGsGenerative Adversarial Zero-Shot Relational Learning for Knowledge Graphs本文是论文Generative Adversarial Zero-Shot Relationa
2020-12-11
R-MeN: A Relational Memory-based Embedding Model本文前置知识: Self - Attention: 详见Transformer精讲. 2020.12.14: 修正错误. A Relational Memory-based Embedding Model for Triple Cl
2020-12-10
基于轻量级卷积和动态卷积替代的注意力机制本文前置知识: Depthwise Convolution: 详见深度可分离卷积与分组卷积. Attention: 详见Seq2Seq和Attention. Transformer: 详见Transformer精讲. 本文是论文PA
2020-12-05
KG-BERT: BERT for Knowledge Graph Completion本文前置知识: BERT: 详见ELMo, GPT, BERT. 本文是论文KG-BERT: BERT for Knowledge Graph Completion的阅读笔记和个人理解. Basic Idea在先前的KGE方法中,
2020-11-28
ConvE: Convolutional 2D Knowledge Graph Embeddings本文前置知识: CNN 本文是论文Convolutional 2D Knowledge Graph Embeddings的阅读笔记和个人理解. 与之前在AcrE中提到的ConvE不同, 本文重新对整篇论文进行叙述, 而非仅介绍论文中
2020-11-27
深度可分离卷积与分组卷积本文前置知识: CNN: 详见卷积神经网络小结. 本文着重介绍深度可分离卷积和分组卷积两种操作. 深度可分离卷积深度可分离卷积(Depthwise Separable Convolution)应用在MobileNet和Xceptio
2020-11-26
Pytorch实现: Transformer本文前置知识: Pytorch基本操作 Transformer: 详见Transformer精讲 2022.04.03: 去掉了Pre Norm比Post Norm效果好的表述. Pytorch实现: Transformer本文是T
2020-11-23