This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Hackable and optimized Transformers building blocks, supporting a composable construction.

A concise but complete full-attention transformer with a set of promising experimental features from various papers

A collection of important graph embedding, classification and representation learning papers with implementations.

A Tensorflow implementation of CapsNet(Capsules Net) in paper Dynamic Routing Between Capsules

Sequence to Sequence Learning with Keras

Keras Attention Layer (Luong and Bahdanau scores).

Learning to Rank in TensorFlow

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"

Longformer: The Long-Document Transformer

Benchmark datasets, data loaders, and evaluators for graph machine learning

proof of concept for a transformer-based time series prediction model

An intuitive library to extract features from time series.

A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).

tfts: Time Series Deep Learning Models in TensorFlow

Multivariate Time Series Transformer, public version

Attention mechanism for processing sequential data that considers the context for each timestamp.

Keras library for building (Universal) Transformers, facilitating BERT and GPT models

PyTorch implementation of some attentions for Deep Learning Researchers.

CapsLayer: An advanced library for capsule theory

Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.

Tensorflow implementation of Amazon DeepAR

Keras implementation of Non-local Neural Networks

tsl: a PyTorch library for processing spatiotemporal data.

Reproducing the paper: "Time2Vec: Learning a Vector Representation of Time" - https://arxiv.org/pdf/1907.05321.pdf

PyTorch implementation of Transformer model used in "Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case"

PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting

[CIKM 2021 Resource Paper] DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction (Graph Part)