Stars
PyTorch Implementation of "TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting" (ICML 2025)
[KDD 2025 Most Influential Paper] DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
[ICML 2025] Official repository of the TQNet paper: "Temporal Query Network for Efficient Multivariate Time Series Forecasting". This work is developed by the Lab of Professor Weiwei Lin (linww@scu…
[TMLR 2025] This is the official code of our Paper "DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting"
The CausalRivers benchmark package. Evaluate your Causal Discovery method on real-world data.
RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks
History matching using Proxy Capacitance-Resistance Model (Gubanova et al., 2022) for producer well shut-in
Capacitance resistance models for waterflood connectivity
[SIGKDD'2025] Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective
The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".
PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)
Official PyTorch Implementation for Fast Adaptive Multitask Optimization (FAMO)
Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning
Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning adjustable weight coefficients.
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"
[ICML 2024] A novel, efficient lightweight approach combining convolutional operations with adaptive spectral analysis as a foundation model for different time series tasks
FinGAT: A Financial Graph Attention Networkto Recommend Top-K Profitable Stocks
The official implementation of LIFT (ICLR'24). Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators.
GMAN: A Graph Multi-Attention Network for Traffic Prediction (GMAN, https://fanxlxmu.github.io/publication/aaai2020/) was accepted by AAAI-2020.
Implementation of Diffusion Convolutional Recurrent Neural Network in Tensorflow
A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.
[IJCAI-24] Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting
Official implementation for the IJCAI'24 paper: SDformer
Official implementation of SAMformer, a transformer leveraging Sharpness-Aware Minimization and Channel-Wise Attention for Time Series Forecasting.