这篇笔记用于收藏别人的论文解读
Social Diffusion
| Title | Unscramble |
|---|---|
| Social Influence Locality for Modeling Retweeting Behavior | 解读 代码 |
| Role-Aware Conformity Influence Modeling and Analysis in Social Network | 解读 |
| DeepInf:Social Influence Prediction with Deep Learning | 解读 |
| Reverse Influence Sampling in Python | 解读及代码 |
| Cost-effective Outbreak Detection in Networks（CELF） | 解读及代码 解读 |
| DeepCas: an End-to-end Predictor of Information Cascades | 解读 |
| Inf2vec: Latent Representation Model for Social Influence Embedding | 解读 |
| POI2Vec: Geographical Latent Representation for Predicting Future Visitors | 解读 |
Network Embedding and GNN
| Title | Unscramble |
|---|---|
| Heterogeneous Graph Attention Network | 解读 |
| Attributed Social Network Embedding | 解读 |
| Self-Translation Network Embedding | 解读1 解读2 |
| Self-Paced Network Embedding | 解读 |
| CANE: Context-Aware Network Embedding for Relation Modeling | 解读 |
| HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning | 解读1 解读2 |
| Embedding Temporal Network via Neighborhood Formation | 解读 |
| Network Representation Learning with Rich Text Information | 解读1 解读2 |
| Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks | 解读 |
| SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction | 解读 |
| Context-Aware Network Embedding for Relation Modeling | 解读 |
| GAN在网络特征学习中的应用 | this |
| 一文读懂「Attention is All You Need」 附代码实现 | 解读 |
| node2vec: Scalable Feature Learning for Networks | 解读1 解读2 解读3 |
| PTE:Predictive Text Embedding through Large-scale | 解读 |
| struc2vec: Learning Node Representations from Structural Identity | 解读 |
| AspEm: Embedding Learning by Aspects in HINs | 解读 |
| Max-Margin DeepWalk: Discriminative Learning of Network Representation | 解读1 解读2 |
| Structural Deep Network Embedding | 解读 |
| Learning Structural Node Embeddings via Diffusion Wavelets | 解读 |
| HARP: Hierarchical Representation Learning for Networks | 解读 |
| Dynamic Network Embedding by Modeling Triadic Closure Process | 解读 |
| RaRE: Social Rank Regulated Large-scale Network Embedding | 解读 |
| TransNet: Translation-Based Network Representation Learning for Social Relation Extraction | 解读 |
| GraphGAN: Graph Representation Learning with Generative Adversarial Nets | 解读 |
| Graph Convolutional Network | 解答 |
| GraRep: Learning Graph Representations with Global Structural Information | 解读 |
| Deep Dynamic Network Embedding for Link Prediction | 解读 |
| Representation Learning for Attributed Multiplex Heterogeneous Network | GATNE |
| Inductive Representation Learning on Large Graphs | GraphSAGE |
| Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba | 解读 |
| Graph Convolutional Neural Networks for Web-Scale Recommender Systems | PinSAGE |
| Semi-Supervised Classification with Graph Convolutional Networks | Semi-GCN |
| Joint Type Inference on Entities and Relations via Graph Convolutional Networks | 解读 |
| 图卷积神经网络（GCN） | GCN |
| Adaptive SamplingTowards Fast Graph Representation Learning | 解读 |
| ProNE: Fast and Scalable Network Representation Learning | ProNE |
| ROTATE:Knowledge graph embedding by relational rotate in complex space | Rotate |
| Signed Graph Convolutional Network | SGCN |
| GAT: Graph Attention Network | GAT GAT2 |
| Large-Scale Learnable Graph Convolutional Networks | LGCN LGCN2 LGCN3 LGCN4 LGCN5 代码分析 |
| Hierarchical Graph Representation Learning with Differentiable Pooling | DiffPool DiffPool |
ML & DL
| Title | Unscramble |
|---|---|
| 常见散度与距离(KL散度，JS散度，Wasserstein距离，互信息MI) | Here |
| 【简化数据】奇异值分解(SVD) | Here |
| AUC的计算与近似 | Here |
| PCA | Here Here Here |
| AdaBoost | Here Here |
| Batch Normalization | Here |
| 矩阵的正定及半正定 | Here |
| 精确率、召回率、F1 值、ROC、AUC | Here |
| Hierarchical Softmax | Here |
| 傅立叶变换 | Here |
| 卷积神经网络（CNN）之一维卷积、二维卷积、三维卷积详解 | Here |
| 变分自编码器（VAE） | Here |
工具
| Title | Unscramble |
|---|---|
| tf.slice() | Here |
| tf.tile() | Here |
| TensorFlow中global_step的简单分析 | Here |
| tensorflow之tf.nn.l2_normalize与l2_loss的计算 | Here |
| tf.nn.top_k() | Here |
| python中matplotlib的颜色及线条控制 | Here |
| python set(集合) & 与 and 与 or之间的区别 | Here |
| numpy实现top_k | Here |
| np reshape(-1,1) | Here |
| 傅里叶变换 | Here Here Here |
技术博客
https://davidham3.github.io/blog
