PathNet: Evolution Channels Gradient Descent in Super Neural Networks

TL;DR

PathNet introduces a neural network method where agents discover and reuse network pathways for different tasks, enabling efficient transfer learning and improved robustness across various supervised and reinforcement learning tasks.

Contribution

It presents a novel pathway-based approach with genetic algorithms for transfer learning in neural networks, demonstrating positive transfer and robustness improvements.

Findings

Successful transfer learning across multiple datasets and tasks.

Paths evolved on earlier tasks re-used parts of optimal paths for new tasks.

Enhanced robustness to hyperparameters in reinforcement learning.

Abstract

For artificial general intelligence (AGI) it would be efficient if multiple users trained the same giant neural network, permitting parameter reuse, without catastrophic forgetting. PathNet is a first step in this direction. It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks. Agents are pathways (views) through the network which determine the subset of parameters that are used and updated by the forwards and backwards passes of the backpropogation algorithm. During learning, a tournament selection genetic algorithm is used to select pathways through the neural network for replication and mutation. Pathway fitness is the performance of that pathway measured according to a cost function. We demonstrate successful transfer learning; fixing the parameters along a path learned on task A and re-evolving a new population of paths for task B, allows task B to be learned faster than it could be learned from scratch or after fine-tuning. Paths evolved on task B re-use parts of the optimal path evolved on task A. Positive transfer was demonstrated for binary MNIST, CIFAR, and SVHN supervised learning classification tasks, and a set of Atari and Labyrinth reinforcement learning tasks, suggesting PathNets have general applicability for neural network training. Finally, PathNet also significantly improves the robustness to hyperparameter choices of a parallel asynchronous reinforcement learning algorithm (A3C).