Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
This addresses the problem of inefficient parallelization and biological implausibility in deep learning training for researchers and practitioners, though it is incremental as it builds on prior work but extends applicability.
The paper tackled the scalability of Direct Feedback Alignment as an alternative to backpropagation, showing it successfully trains state-of-the-art deep learning architectures across diverse tasks like neural view synthesis and natural language processing, with performance close to fine-tuned backpropagation.
Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged. Alternative schemes have been devised; yet, under the constraint of synaptic asymmetry, none have scaled to modern deep learning tasks and architectures. Here, we challenge this perspective, and study the applicability of Direct Feedback Alignment to neural view synthesis, recommender systems, geometric learning, and natural language processing. In contrast with previous studies limited to computer vision tasks, our findings show that it successfully trains a large range of state-of-the-art deep learning architectures, with performance close to fine-tuned backpropagation. At variance with common beliefs, our work supports that challenging tasks can be tackled in the absence of weight transport.