Network Classifiers With Output Smoothing
This work addresses the challenge of cooperative learning in distributed networks with heterogeneous agents, offering a solution for domains like sensor networks or IoT where feature dimensions vary, though it appears incremental as it builds on existing smoothing techniques.
The paper tackles the problem of training network classifiers with heterogeneous agents that have varying feature sizes, making direct parameter combination infeasible, by proposing two strategies for smoothing classifier outputs to enable cooperation. The result is demonstrated through computer simulations, showing the approach's effectiveness in scenarios where agents have insufficient attributes for reliable individual decisions.
This work introduces two strategies for training network classifiers with heterogeneous agents. One strategy promotes global smoothing over the graph and a second strategy promotes local smoothing over neighbourhoods. It is assumed that the feature sizes can vary from one agent to another, with some agents observing insufficient attributes to be able to make reliable decisions on their own. As a result, cooperation with neighbours is necessary. However, due to the fact that the feature dimensions are different across the agents, their classifier dimensions will also be different. This means that cooperation cannot rely on combining the classifier parameters. We instead propose smoothing the outputs of the classifiers, which are the predicted labels. By doing so, the dynamics that describes the evolution of the network classifier becomes more challenging than usual because the classifier parameters end up appearing as part of the regularization term as well. We illustrate performance by means of computer simulations.