resolutions-2019A list of data mining and machine learning papers that I implemented in 2019.
Stars: ✭ 19 (-56.82%)
FEATHERThe reference implementation of FEATHER from the CIKM '20 paper "Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models".
Stars: ✭ 34 (-22.73%)
Awesome Graph ClassificationA collection of important graph embedding, classification and representation learning papers with implementations.
Stars: ✭ 4,309 (+9693.18%)
gnn-lspeSource code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
Stars: ✭ 165 (+275%)
GraphDeeSmartContractSmart contract vulnerability detection using graph neural network (DR-GCN).
Stars: ✭ 84 (+90.91%)
golgothaContextualised Embeddings and Language Modelling using BERT and Friends using R
Stars: ✭ 39 (-11.36%)
Bert PytorchGoogle AI 2018 BERT pytorch implementation
Stars: ✭ 4,642 (+10450%)
Nlp TutorialNatural Language Processing Tutorial for Deep Learning Researchers
Stars: ✭ 9,895 (+22388.64%)
FSCNMFAn implementation of "Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks".
Stars: ✭ 16 (-63.64%)
KitanaQAKitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (+31.82%)
BGCNA Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).
Stars: ✭ 129 (+193.18%)
GNNs-in-Network-NeuroscienceA review of papers proposing novel GNN methods with application to brain connectivity published in 2017-2020.
Stars: ✭ 92 (+109.09%)
SIGIR2021 ConureOne Person, One Model, One World: Learning Continual User Representation without Forgetting
Stars: ✭ 23 (-47.73%)
bert in a flaskA dockerized flask API, serving ALBERT and BERT predictions using TensorFlow 2.0.
Stars: ✭ 32 (-27.27%)
walkletsA lightweight implementation of Walklets from "Don't Walk Skip! Online Learning of Multi-scale Network Embeddings" (ASONAM 2017).
Stars: ✭ 94 (+113.64%)
semantic-document-relationsImplementation, trained models and result data for the paper "Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles"
Stars: ✭ 21 (-52.27%)
vietnamese-robertaA Robustly Optimized BERT Pretraining Approach for Vietnamese
Stars: ✭ 22 (-50%)
Smiles TransformerOriginal implementation of the paper "SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery" by Shion Honda et al.
Stars: ✭ 86 (+95.45%)
sisterSImple SenTence EmbeddeR
Stars: ✭ 66 (+50%)
TabFormerCode & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
Stars: ✭ 209 (+375%)
dgcnnClean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).
Stars: ✭ 21 (-52.27%)
staginSTAGIN: Spatio-Temporal Attention Graph Isomorphism Network
Stars: ✭ 34 (-22.73%)
kGCNA graph-based deep learning framework for life science
Stars: ✭ 91 (+106.82%)
ASAPAAAI 2020 - ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations
Stars: ✭ 83 (+88.64%)
TDRGTransformer-based Dual Relation Graph for Multi-label Image Recognition. ICCV 2021
Stars: ✭ 32 (-27.27%)
XpersonaXPersona: Evaluating Multilingual Personalized Chatbot
Stars: ✭ 54 (+22.73%)
Walk-TransformerFrom Random Walks to Transformer for Learning Node Embeddings (ECML-PKDD 2020) (In Pytorch and Tensorflow)
Stars: ✭ 26 (-40.91%)
Graph Neural NetGraph Convolutional Networks, Graph Attention Networks, Gated Graph Neural Net, Mixhop
Stars: ✭ 27 (-38.64%)
bert-as-a-service TFXEnd-to-end pipeline with TFX to train and deploy a BERT model for sentiment analysis.
Stars: ✭ 32 (-27.27%)
Filipino-Text-BenchmarksOpen-source benchmark datasets and pretrained transformer models in the Filipino language.
Stars: ✭ 22 (-50%)
BertvizTool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)
Stars: ✭ 3,443 (+7725%)
Transformers🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stars: ✭ 55,742 (+126586.36%)
GNN-Recommender-SystemsAn index of recommendation algorithms that are based on Graph Neural Networks.
Stars: ✭ 505 (+1047.73%)
sticker2Further developed as SyntaxDot: https://github.com/tensordot/syntaxdot
Stars: ✭ 14 (-68.18%)
NLP-paper🎨 🎨NLP 自然语言处理教程 🎨🎨 https://dataxujing.github.io/NLP-paper/
Stars: ✭ 23 (-47.73%)
3DInfomaxMaking self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.
Stars: ✭ 107 (+143.18%)
GraphMixCode for reproducing results in GraphMix paper
Stars: ✭ 64 (+45.45%)
FasterTransformerTransformer related optimization, including BERT, GPT
Stars: ✭ 1,571 (+3470.45%)
Kevinpro-NLP-demoAll NLP you Need Here. 个人实现了一些好玩的NLP demo,目前包含13个NLP应用的pytorch实现
Stars: ✭ 117 (+165.91%)
QGNNQuaternion Graph Neural Networks (ACML 2021) (Pytorch and Tensorflow)
Stars: ✭ 31 (-29.55%)
tfbert基于tensorflow1.x的预训练模型调用,支持单机多卡、梯度累积,XLA加速,混合精度。可灵活训练、验证、预测。
Stars: ✭ 54 (+22.73%)
NiuTrans.NMTA Fast Neural Machine Translation System. It is developed in C++ and resorts to NiuTensor for fast tensor APIs.
Stars: ✭ 112 (+154.55%)
mirror-bert[EMNLP 2021] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.
Stars: ✭ 56 (+27.27%)
parsbert-ner🤗 ParsBERT Persian NER Tasks
Stars: ✭ 15 (-65.91%)
JD2Skills-BERT-XMLCCode and Dataset for the Bhola et al. (2020) Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework
Stars: ✭ 33 (-25%)
YOLOSYou Only Look at One Sequence (NeurIPS 2021)
Stars: ✭ 612 (+1290.91%)
BERT-embeddingA simple wrapper class for extracting features(embedding) and comparing them using BERT in TensorFlow
Stars: ✭ 24 (-45.45%)
TransPosePyTorch Implementation for "TransPose: Keypoint localization via Transformer", ICCV 2021.
Stars: ✭ 250 (+468.18%)
bert-squeeze🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
Stars: ✭ 56 (+27.27%)
verseagilityRamp up your custom natural language processing (NLP) task, allowing you to bring your own data, use your preferred frameworks and bring models into production.
Stars: ✭ 23 (-47.73%)