The titles without a hyperlink are to be written, and would be updated soon 🙇🏻♂️

- 🐷 = fundamental theories
- 👨👩👧👦 = series of papers on a same topic
- 🐶 = a single paper

## 1 **Maths**

### 1.1 Linear Algebra & Functional Analysis

### 1.2 Probability & Statistics

### 1.3 Optimization & Numerical Computation

- 🐷 Stochastic Gradient Descent (SGD)
- 🐷 Alternating Direction Method of Multipliers (ADMM)
- 🐶 The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices

## 2 **ML**

### 2.1 Fundamentals

- 🐷 My notes on
*Fundamentals of Machine Learning (2nd edition)* - 🐷 Regularization Theories
- 🐷 Kernel Function / Method / Trick

### 2.2 Deep Clustering & Subspace Clustering

- 🐶 Unsupervised deep embedding for clustering analysis. (ICML 2016, DEC)
- 🐶 Joint Unsupervised Learning of Deep Representations and Image Clusters (CVPR 2016, JULE)
- 👨👩👧👦 Sparse self representation subspace clustering
- including papers: SSC, SSSC, SSConvSCN

- 🐶 Low rank representation subspace clustering
- math fundamental: 🐷 low rank matrix factorization

### 2.3 Spectral Methods & GNN

- 🐷 Spectral Clustering
- 🐷 Spectra of Simple Graphs
- 🐷 Graph Fourier Transformation & convolution
- 🐶 Semi-Supervised Classification with Graph Convolutional Network (ICML 2017, GCN)

### 2.4 Few-shot Learning

#### – Data Augmentation

#### – Metric Learning

- 🐶 Siamese neural networks for one-shot image recognition (ICML 2015, Siamese Net)
- 🐶 Matching networks for one shot learning (NeuralIPS 2016, Matching Net)
- 🐶 Prototypical Networks for Few-shot Learning (NeuralIPS 2017, Prototypical Net)
- 🐶 Learning to Compare: Relation Network for Few-Shot Learning (CVPR 2018, Relation Net)

#### – Meta Optimizer Based

- 🐶 Optimization as a Model for Few-Shot Learning (ICLR 2017, meta-LSTM)
- 🐶 Model-agnostic meta-learning for fast adaptation of deep networks (ICML 2017, MAML)

#### – Applications in NLP

- 🐶 Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (ACL 2020, L-TapNet + CDT)

## 3 **NLP**

### 3.1 Fundamentals

- 🐷 Word2vec
- 🐷 HMM & CRF
- 🐷 Attention
- 👨👩👧👦 Pre-trained Models

### 3.2 Information Extraction

#### – Sequence Labelling

#### – Neural Relation Extraction

- 🐶 Integrating Relation Constraints with Neural Relation Extractors (AAAI 2020, CLC)

#### – Relational Triple Extraction

- 🐶 Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme (ACL 2017)
- 🐶 Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism (ACL 2018)
- 🐶 A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (ACL 2020, CasREL)

#### – Event Extraction

- 👨👩👧👦 Survey of event extraction
- 🐶 Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks (ACL 2015, DMCNN)
- 🐶 Joint Event Extraction via Recurrent Neural Networks (ACL 2016, JRNN)
- 🐶 A Convolution BiLSTM Neural Network Model for Chinese Event Extraction (NLPCC 2016, CNN + BiLSTM)
- 🐶 Scale Up Event Extraction Learning via Automatic Training Data Generation (AAAI 2018, BiLSTM + CRF + ILP + CVT)
- 🐶 Adversarial Training for Weakly Supervised Event Detection (NAACL 2019, Adv-ED)

### 3.3 Knowledge Graph

#### – Knowledge Representation Learning

- 🐶 Translating Embeddings for Modeling Multi-relational Data (NeurIPS 2013, TransE)

#### – Entity Alignment

- 🐶 Neighborhood Matching Network for Entity Alignment (ACL 2020, NMN)