JonathanCrabbe / Dynamask
This repository contains the implementation of Dynamask, a method to identify the features that are salient for a model to issue its prediction when the data is represented in terms of time series. For more details on the theoretical side, please read our ICML 2021 paper: 'Explaining Time Series Predictions with Dynamic Masks'.
☆75Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Dynamask
- ☆60Updated 3 years ago
- ☆86Updated 3 years ago
- Unified Model Interpretability Library for Time Series☆44Updated 10 months ago
- Repository of the ICML 2020 paper "Set Functions for Time Series"☆121Updated 3 years ago
- Contrastive Learning for Time Series☆38Updated last year
- Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.☆121Updated 3 years ago
- [SDM 2022] Towards Similarity-Aware Time-Series Classification☆73Updated last year
- Causal Neural Nerwork☆82Updated 7 months ago
- ☆112Updated last year
- Code for paper titled "Learning Latent Seasonal-Trend Representations for Time Series Forecasting" in NeurIPS 2022☆73Updated 2 years ago
- Counterfactual Explanations for Multivariate Time Series Data☆29Updated 8 months ago
- Feature Importance Analysis of Models☆11Updated 2 years ago
- (Under Review)☆66Updated 3 years ago
- ☆68Updated 3 months ago
- Code for "Interpolation-Prediction Networks for Irregularly Sampled Time Series", ICLR 2019.☆94Updated 3 months ago
- A curated list of time series augmentation resources.☆64Updated 2 years ago
- GluonTS - Probabilistic Time Series Modeling in Python☆51Updated 3 years ago
- Official Implementation of Time Series Generation with Masked Autoencoder (ExtraMAE)☆35Updated 2 years ago
- ☆28Updated 3 months ago
- Code for our NeurIPS 2020 paper "Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversity"☆87Updated 3 years ago
- Domain Adaptation for Time Series Under Feature and Label Shifts☆107Updated last year
- Implementation of the InterpretTime framework☆39Updated last year
- Implementation for Stankevičiūtė et al. "Conformal time-series forecasting", NeurIPS 2021.☆65Updated 2 weeks ago
- This repository contains the source code for time series regression.☆95Updated last year
- ☆37Updated last year
- Causal discovery for time series☆90Updated 2 years ago
- PyTorch Implementation of GRU-D from "Recurrent Neural Networks for Multivariate Time Series with Missing Values" https://arxiv.org/abs/1…☆24Updated 4 years ago
- Time series explainability via self-supervised model behavior consistency☆38Updated last year
- Time Series Change Point Detection based on Contrastive Predictive Coding☆72Updated 2 years ago