Mitigating Catastrophic Forgetting in Long Short-Term Memory Networks
This addresses catastrophic forgetting in LSTMs for continual learning, which is critical for ML deployments in sequential data domains like computer systems and NLP, offering a simple and effective incremental improvement over existing methods.
The paper tackles catastrophic forgetting in LSTM networks for continual learning on sequential data by proposing two simple methods that separate LSTM memory per task or label, eliminating the need for complex regularization. It demonstrates effectiveness in computer memory access prefetching, enabling faster learning compared to state-of-the-art weight regularization methods, and extends applicability to small, non-regularized LSTMs in offline natural language processing.
Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their ability to learn multiple tasks continually. We discover that catastrophic forgetting in LSTM networks can be overcome in two novel and readily-implementable ways -- separating the LSTM memory either for each task or for each target label. Our approach eschews the need for explicit regularization, hypernetworks, and other complex methods. We quantify the benefits of our approach on recently-proposed LSTM networks for computer memory access prefetching, an important sequential learning problem in ML-based computer system optimization. Compared to state-of-the-art weight regularization methods to mitigate catastrophic forgetting, our approach is simple, effective, and enables faster learning. We also show that our proposal enables the use of small, non-regularized LSTM networks for complex natural language processing in the offline learning scenario, which was previously considered difficult.