Sign-Symmetry Learning Rules are Robust Fine-Tuners
This work is significant for researchers in the field of deep learning, particularly those interested in biologically inspired learning rules, as it provides an incremental yet valuable step towards leveraging such rules in standard neural network training.
The authors tackled the problem of integrating biologically plausible learning mechanisms into standard neural network training pipelines and achieved performance parity with backpropagation while enhancing robustness. They demonstrated the validity of their approach through extensive experiments across multiple tasks and benchmarks.
Backpropagation (BP) has long been the predominant method for training neural networks due to its effectiveness. However, numerous alternative approaches, broadly categorized under feedback alignment, have been proposed, many of which are motivated by the search for biologically plausible learning mechanisms. Despite their theoretical appeal, these methods have consistently underperformed compared to BP, leading to a decline in research interest. In this work, we revisit the role of such methods and explore how they can be integrated into standard neural network training pipelines. Specifically, we propose fine-tuning BP-pre-trained models using Sign-Symmetry learning rules and demonstrate that this approach not only maintains performance parity with BP but also enhances robustness. Through extensive experiments across multiple tasks and benchmarks, we establish the validity of our approach. Our findings introduce a novel perspective on neural network training and open new research directions for leveraging biologically inspired learning rules in deep learning.