Open-source alternatives to Pathformer

This repository is a collection of practical deep learning implementations and examples built using the TensorFlow framework. It provides a variety of neural network architectures focusing on natural language processing, recommendation systems, reinforcement learning, and time series prediction. The project features a range of specialized models, including sequence-to-sequence and transformer architectures for text processing, and factorization machines for personalized ranking and retrieval. It also includes implementations of reinforcement learning agents using actor-critic and policy gradi

Implementation of the paper "Performative Time-Series Forecasting."

Implementation of the paper "LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting."

We require you to have anaconda or miniconda installed. Run the script ./scripts/setup.sh to setup the virtual environment with all the required packages.

(NeurIPS 2024 Spotlight) 🌟 Paper Link

中文解读1 中文解读2 中文解读3

This is a Official PyTorch implementation of CLCRN in the following paper:

Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting, ICLR 2023

This repo provides an implementation of the FC-GAGA algorithm introduced in https://arxiv.org/abs/2007.15531 and reproduces the experimental results presented in the paper.

This is a PyTorch implementation of the paper "Discrete Graph Structure Learning for Forecasting Multiple Time Series", ICLR 2021.

Dependencies can be installed using the following file: newtimelibenvironment.yml You can obtain the well pre-processed datasets from [Google Drive](https://drive.google.com/drive/folders/13Cg1KYOlzM5C7K8gK8NfC-F3EYxkM3D2?usp=sharing) or [[Baidu…

(AAAI'25) TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment

1. Install requirements. `pip install -r requirements.txt`

This is the official implementation of "Neural Conformal Control for Time Series Forecasting" (NCC) appearing in AAAI 2025 (main track). Authors are Ruipu Li and Alexander Rodríguez from the University of Michigan.

The repo is the official implementation for the paper: CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations (ICML'25).

Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, Rong Jin, "FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting," in Proc. 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland, July 17-23, 2022. paper

Weiqi Chen, Wenwei Wang, Bingqing Peng, Qingsong Wen, Tian Zhou, Liang Sun, "Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting" in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022), 2022. paper

AAAI 2020. Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting

This is the official repo for "Auto-Regressive Moving Diffusion Models for Time Series Forecasting".

This code is the official PyTorch implementation of our ICML'25 Spotlight Paper: K 2 VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

This code is the official PyTorch implementation of our ICML'25 Poster Paper: LightGTS: A Lightweight General Time Series Forecasting Model

TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods

This is an extended journal version of the below conference paper.

CATS removes self-attention and retains only cross-attention in its transformer architecture. This design choice aims to better preserve temporal information in time series forecasting, addressing the potential loss of such information during the embedding process in traditional transformer models.

SC data: the dataset contains power grid series of 133 locations, and the location index, date, hour, temperature, precipitation, active power and reactive power is reported in the dataset.