Pinned Repositories
Data-poisoning-attacks-on-factorization-based-collaborative-filtering
Data poisoning attack of recommend system using the algorithm of MF.
DeepLearning
包括但不限于：DNN、AutoEncoder、CNN、RNN等
Entity-Linking
Entity Linking，识别给定文本中出现的命名实体（Named Entity），并映射到特定的知识库中唯一的实体。包括命名实体识别、消歧等工作。
Graph-Embedding
对Graph上顶点、边进行特征提取相关工作学习
MatchingNetworks
An attempt at replicating the Matching Networks for One Shot Learning in Tensorflow - Paper URL: https://arxiv.org/pdf/1606.04080.pdf
ML
Sum up some frequently used machine learning algorithms and data analysis methods using Python language.
Model-Alan
对机器学习、概率图模型、主题模型领域一些模型进行实现，主要涉及一些近年高水平会议论文中提到的算法。
PLNLP
Pairwise learning neural link prediction for ogb link prediction
UniWalk
We design a Monte Carlo based method, UniWalk, to enable the fast top-k SimRank computation over large undirected graphs. UniWalk directly locates the top-k similar vertices for any single source vertex u via approximately R sampling paths originating from u only. Related work has been published in ICDE 2017 ("UniWalk: Unidirectional Random Walk Based Scalable SimRank Computation over Large Graph"). Furthermore, in order to overcome the "rectification issue" in the original UniWalk, we design a path enumeration strategy to gain higher precision, which computes SimRank with the path probabilities instead of path frequencies in sampling. We call it the optimized UniWalk here, which is shown in the "UniWalk/src/simrank/SingleRandomDev.java" file(the basic UniWalk is shown in "UniWalk/src/simrank/SingleRandomWalk.java").
distance-encoding
Distance Encoding for GNN Design
Junshuai-Song's Repositories
Junshuai-Song/Entity-Linking
Entity Linking，识别给定文本中出现的命名实体（Named Entity），并映射到特定的知识库中唯一的实体。包括命名实体识别、消歧等工作。
Junshuai-Song/UniWalk
We design a Monte Carlo based method, UniWalk, to enable the fast top-k SimRank computation over large undirected graphs. UniWalk directly locates the top-k similar vertices for any single source vertex u via approximately R sampling paths originating from u only. Related work has been published in ICDE 2017 ("UniWalk: Unidirectional Random Walk Based Scalable SimRank Computation over Large Graph"). Furthermore, in order to overcome the "rectification issue" in the original UniWalk, we design a path enumeration strategy to gain higher precision, which computes SimRank with the path probabilities instead of path frequencies in sampling. We call it the optimized UniWalk here, which is shown in the "UniWalk/src/simrank/SingleRandomDev.java" file(the basic UniWalk is shown in "UniWalk/src/simrank/SingleRandomWalk.java").
Junshuai-Song/Data-poisoning-attacks-on-factorization-based-collaborative-filtering
Data poisoning attack of recommend system using the algorithm of MF.
Junshuai-Song/MatchingNetworks
An attempt at replicating the Matching Networks for One Shot Learning in Tensorflow - Paper URL: https://arxiv.org/pdf/1606.04080.pdf
Junshuai-Song/PLNLP
Pairwise learning neural link prediction for ogb link prediction
Junshuai-Song/A-DEEP-REINFORCED-MODEL-FOR-ABSTRACTIVE-SUMMARIZATION
Pytorch implementation for paper of "A DEEP REINFORCED MODEL FOR ABSTRACTIVE SUMMARIZATION". https://arxiv.org/abs/1705.04304
Junshuai-Song/AAAI18-code
The code of AAAI18 paper "Learning Structured Representation for Text Classification via Reinforcement Learning".
Junshuai-Song/Actor_CriticPointer_Network-TSP
Tensorflow implementation of an Actor Critic algorithm using a Pointer Network to solve the TSP (algorithm from Neural Combinatorial Optimization with Reinforcement Learning, Bello et al, 2016)
Junshuai-Song/adversarial-mt
Code for "Imitation Attacks and Defenses for Black-box Machine Translations Systems"
Junshuai-Song/AdvSSL
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
Junshuai-Song/awesome-chatgpt-prompts-zh
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
Junshuai-Song/CNTK
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Junshuai-Song/Deep-Reinforcement-Learning-in-Large-Discrete-Action-Spaces
Implementation of the algorithm in Python 3, TensorFlow and OpenAI Gym
Junshuai-Song/DeFrauder
Junshuai-Song/Distributed_PPO
This is an pytorch implementation of Distributed Proximal Policy Optimization(DPPO).
Junshuai-Song/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Junshuai-Song/DQN_MVC
Implementation of Learning Combinatorial Optimization Algorithms over Graphs, by Hanjun Dai et al. (2017)
Junshuai-Song/exposure_bias
some strategies for exposure bias in seq2seq
Junshuai-Song/generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Junshuai-Song/graph-fraud-detection-papers
A curated list of fraud detection papers using graph information or graph neural networks
Junshuai-Song/graphnn
Training computational graph on top of structured data (string, graph, etc)
Junshuai-Song/imitation
Code for the paper "Generative Adversarial Imitation Learning"
Junshuai-Song/MCNS
Source code and dataset for KDD 2020 paper "Understanding Negative Sampling in Graph Representation Learning"
Junshuai-Song/Pointer-Networks-1
Junshuai-Song/RelationClassification-RL
Reinforcement Learning for Relation Classification from Noisy Data(AAAI2018)
Junshuai-Song/tensorflow-pointer-networks-1
Pointer Networks in Tensorflow
Junshuai-Song/TextAttack
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
Junshuai-Song/TransNets
Junshuai-Song/universal-triggers
Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)
Junshuai-Song/x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers