Distilling the Knowledge in a Neural Network本文是论文Distilling the Knowledge in a Neural Network的阅读笔记和个人理解. Basic Idea现有机器学

本文前置知识: BERT: 详见ELMo, GPT, BERT. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations本文是论文AL

本文前置知识: BERT: 详见ELMo, GPT, BERT. UniLM: Unified Language Model Pre-training for Natural Language Understanding and G

本文前置知识; BERT: 详见ELMo, GPT, BERT. Transformer: 详见Transformer精讲. MASS: Masked Sequence to Sequence Pre-training for La

本文前置知识: BERT: 详见ELMo, GPT, BERT. SpanBERT: Improving Pre-training by Representing and Predicting Spans本文是论文SpanBERT:

本文前置知识: BERT: 详见ELMo, GPT, BERT. StructBERT: Incorporating Language Structures into Pre-training for Deep Language U

本文前置知识: Transformer: 详见Transformer精讲. BERT, GPT: 详见ELMo, GPT, BERT. BART和mBART本文是如下论文的阅读笔记和个人理解: BART: Denoising

GAKE: Graph Aware Knowledge Embedding本文是论文GAKE: Graph Aware Knowledge Embedding的阅读笔记和个人理解. Basic Idea在现有的KGE方法中, 都是基于三元组

本文前置知识: RotatE: 详见RotatE: Relational Rotation in Complex Vector Space Learning Hierarchy-Aware Knowledge Graph Embed

ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for KGE本文是论文ReInceptionE:

本文前置知识: GAT: 详见图神经网络入门. Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs本文是论文Learning

本文前置知识: GCN: 详见图神经网络入门 R - GCN: 详见R - GCN: Modeling Relational Data with Graph Convolutional Networks Composition-ba