Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning

TL;DR

This paper introduces a decomposed plasticity rule for meta-learning in neural networks, enabling efficient adaptation and improved generalization by reducing meta-parameters and studying neural modulation effects.

Contribution

It proposes a novel neuron-dependent plasticity rule that decomposes connection-dependent rules, aligning with the genomics bottleneck, and demonstrates its effectiveness in maze navigation tasks.

Findings

Plasticity-enhanced RNNs outperform pre-trained models in long-term memory tasks.

Decomposed plasticity rules are comparable or superior to canonical rules in certain scenarios.

Neural modulation significantly influences the effectiveness of plasticity in learning.

Abstract

Artificial neural networks (ANNs) are typically confined to accomplishing pre-defined tasks by learning a set of static parameters. In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e.g., meta-learning. Among various biologically inspired learning rules, Hebbian plasticity updates the neural network weights using local signals without the guide of an explicit target function, thus enabling an agent to learn automatically without human efforts. However, typical plastic ANNs using a large amount of meta-parameters violate the nature of the genomics bottleneck and potentially deteriorate the generalization capacity. This work proposes a new learning paradigm decomposing those connection-dependent plasticity rules into neuron-dependent rules thus accommodating $\Theta(n^2)$ learnable parameters with only $\Theta(n)$ meta-parameters. We also thoroughly study the effect of different neural modulation on plasticity. Our algorithms are tested in challenging random 2D maze environments, where the agents have to use their past experiences to shape the neural connections and improve their performances for the future. The results of our experiment validate the following: 1. Plasticity can be adopted to continually update a randomly initialized RNN to surpass pre-trained, more sophisticated recurrent models, especially when coming to long-term memorization. 2. Following the genomics bottleneck, the proposed decomposed plasticity can be comparable to or even more effective than canonical plasticity rules in some instances.