jc-audet / WOODS
Benchmarks for Out-of-Distribution Generalization in Time Series Tasks
☆69Updated 2 years ago
Alternatives and similar repositories for WOODS:
Users that are interested in WOODS are comparing it to the libraries listed below
- Implementation of the InterpretTime framework☆45Updated 2 years ago
- Contrastive Learning for Time Series☆38Updated 2 years ago
- Contrastive Learning for Domain Adaptation of Time Series☆89Updated last year
- ☆91Updated 3 years ago
- Domain Adaptation for Time Series Under Feature and Label Shifts☆119Updated last year
- This repository contains the implementation of Dynamask, a method to identify the features that are salient for a model to issue its pred…☆75Updated 2 years ago
- Code for mixup contrastive learning☆22Updated 4 years ago
- [TAI 2023] Contrastive Domain Adaptation for Time-Series via Temporal Mixup☆30Updated last year
- ☆72Updated last year
- GitHub Repo for ICLR 2023 Paper "Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks"☆60Updated 2 years ago
- Implementation of the ICML 2024 paper "Discovering Mixtures of Structural Causal Models from Time Series Data"☆21Updated 6 months ago
- ☆60Updated 4 years ago
- MHCCL: Masked Hierarchical Cluster-wise Contrastive Learning for Multivariate Time Series - a PyTorch Version (AAAI-2023)☆39Updated 9 months ago
- Multivariate Time Series Classification Model with Attentional Prototype Network☆44Updated 6 years ago
- Time series explainability via self-supervised model behavior consistency☆47Updated last year
- Segment, Shuffle, and Stitch: A Simple Mechanism for Improving Time-Series Representations☆27Updated 6 months ago
- A benchmark for distribution shift in tabular data☆52Updated 10 months ago
- ☆19Updated last week
- ULTS: A unified and standardized library of unsupervised representation learning approaches for time series☆47Updated last year
- (Under Review)☆67Updated 3 years ago
- ☆26Updated 2 years ago
- [KDD2024] Class-incremental Learning for Time Series: Benchmark and Evaluation☆50Updated 10 months ago
- A comparative study on Self-Supervised Learning for Time Series: Contrastive or Generative?☆33Updated last year
- Code for the paper "Rethinking Importance Weighting for Deep Learning under Distribution Shift".☆30Updated 4 years ago
- ☆37Updated last year
- Code for "Generalised Interpretable Shapelets for Irregular Time Series"☆57Updated last year
- Contrastive Adversarial Learning for Multi-Source Time Series Domain Adaptation☆28Updated 3 years ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆66Updated 2 years ago
- DBPM is a simple algorithm designed as a lightweight plug-in without learnable parameters to enhance the performance of time series contr…☆15Updated last year
- [Nature Communications 2021] Continual learning of AI models on ECG data with CLOPS☆20Updated 2 years ago