Autonomous and Ubiquitous In-node Learning Algorithms of Active Directed Graphs and Its Storage Behavior

TL;DR

This paper introduces a decentralized, active-directed graph algorithm for in-node information storage inspired by neural engram theory, demonstrating improved robustness and capacity in sparse networks.

Contribution

It proposes a novel parallel distributed storage algorithm based on active-directed graphs with autonomous nodes, differing from traditional global-view algorithms.

Findings

Larger network capacity in sparse structures.

Enhanced fault tolerance and robustness.

Distributed algorithm performs well without global control.

Abstract

Memory is an important cognitive function for humans. How a brain with such a small power can complete such a complex memory function, the working mechanism behind this is undoubtedly fascinating. Engram theory views memory as the co-activation of specific neuronal clusters. From the perspective of graph theory, nodes represent neurons, and directed edges represent synapses. Then the memory engram is the connected subgraph formed between the activated nodes. In this paper, we use subgraphs as physical carriers of information and propose a parallel distributed information storage algorithm based on node scale in active-directed graphs. An active-directed graph is defined as a graph in which each node has autonomous and independent behavior and relies only on information obtained within the local field of view to make decisions. Unlike static directed graphs used for recording facts, active-directed graphs are decentralized like biological neuron networks and do not have a super manager who has a global view and can control the behavior of each node. Distinct from traditional algorithms with a global field of view, this algorithm is characterized by nodes collaborating globally on resource usage through their limited local field of view. While this strategy may not achieve global optimality as well as algorithms with a global field of view, it offers better robustness, concurrency, decentralization, and bioviability. Finally, it was tested in network capacity, fault tolerance, and robustness. It was found that the algorithm exhibits a larger network capacity in a more sparse network structure because the subgraph generated by a single sample is not a whole but consists of multiple weakly connected components. In this case, the network capacity can be understood as the number of permutations of several weakly connected components in the network.