Global Collaboration through Local Interaction in Competitive Learning
This work reduces algorithmic complexity and enables distributed self-organizing maps, addressing scalability in competitive learning.
The paper tackled the problem of forming feature maps that preserve global topology, showing that strictly local interactions among competing agents can uncover global topology without global interaction, and demonstrated scalability with a linear relation between training time and dataset size.
Feature maps, that preserve the global topology of arbitrary datasets, can be formed by self-organizing competing agents. So far, it has been presumed that global interaction of agents is necessary for this process. We establish that this is not the case, and that global topology can be uncovered through strictly local interactions. Enforcing uniformity of map quality across all agents, results in an algorithm that is able to consistently uncover the global topology of diversely challenging datasets.The applicability and scalability of this approach is further tested on a large point cloud dataset, revealing a linear relation between map training time and size. The presented work not only reduces algorithmic complexity but also constitutes first step towards a distributed self organizing map.