Overcoming Catastrophic Forgetting by XAI
This work addresses the problem of catastrophic forgetting in continual learning for AI systems, offering both explainability and performance improvements, though it appears incremental in combining interpretability with existing learning methods.
The paper tackles catastrophic forgetting in continual learning by proposing a novel tool, Catastrophic Forgetting Dissector (CFD), to explain the phenomenon and introducing a new method called Critical Freezing based on these insights. Their algorithm defeats various recent techniques by a significant margin, demonstrating its effectiveness.
Explaining the behaviors of deep neural networks, usually considered as black boxes, is critical especially when they are now being adopted over diverse aspects of human life. Taking the advantages of interpretable machine learning (interpretable ML), this work proposes a novel tool called Catastrophic Forgetting Dissector (or CFD) to explain catastrophic forgetting in continual learning settings. We also introduce a new method called Critical Freezing based on the observations of our tool. Experiments on ResNet articulate how catastrophic forgetting happens, particularly showing which components of this famous network are forgetting. Our new continual learning algorithm defeats various recent techniques by a significant margin, proving the capability of the investigation. Critical freezing not only attacks catastrophic forgetting but also exposes explainability.