Renate is a Python package for automatic retraining of neural networks models. It uses advanced Continual Learning and Lifelong Learning algorithms to achieve this purpose. The implementation is based on PyTorch and Lightning for deep learning, and Syne Tune for hyperparameter optimization.
- Install renate with
pip install renateor look at these instructions - Examples for local training and training on Amazon SageMaker.
- Documentation
- Supported Algorithms
In many applications data is made available over time and retraining from scratch for every new batch of data is prohibitively expensive. In these cases, we would like to use the new batch of data provided to update our previous model with limited costs. Unfortunately, since data in different chunks is not sampled according to the same distribution, just fine-tuning the old model creates problems like catastrophic forgetting. The algorithms in Renate help mitigating the negative impact of forgetting and increase the model performance overall.
Renate's update mechanisms improve over naive fine-tuning approaches. [1]
Renate also offers hyperparameter optimization (HPO), a functionality that can heavily impact the performance of the model when continuously updated. To do so, Renate employs Syne Tune under the hood, and can offer advanced HPO methods such multi-fidelity algorithms (ASHA) and transfer learning algorithms (useful for speeding up the retuning).
Renate will benefit from hyperparameter tuning compared to Renate with default settings. [2]
- Easy to scale and run in the cloud
- Designed for real-world retraining pipelines
- Advanced HPO functionalities available out-of-the-box
- Open for experimentation
- (blog) Automatically retrain neural networks with Renate
- (paper) Renate: A Library for Real-World Continual Learning
@misc{renate2023, title = {Renate: A Library for Real-World Continual Learning}, author = {Martin Wistuba and Martin Ferianc and Lukas Balles and Cedric Archambeau and Giovanni Zappella}, year = {2023}, eprint = {2304.12067}, archivePrefix = {arXiv}, primaryClass = {cs.LG} }
- Installation Instructions
pip install renate
If you did not find what you were looking for, open an issue and we will do our best to improve the documentation.
| [1] | To create this plot, we simulated domain-incremental learning with CLEAR-100. The training data was divided by year, and we trained sequentially on them. Fine-tuning refers to the strategy to learn on the first partition from scratch, and train on each of the subsequent partitions for few epochs only. We compare to Experience Replay with an infinite memory size. For both methods we use the same amount of training time and choose the best checkpoint using a validation set. Results reported are on the test set. |
| [2] | In this experiment, we consider class-incremental learning on CIFAR-10. We compare Experience Replay against a version in which its hyperparameters were tuned. |