Network Classifiers Based on Social Learning

by   Virginia Bordignon, et al.

This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to streaming data during testing and continue to improve their performance even during this phase. By doing so, the proposed architecture is able to improve prediction performance over time with unlabeled data. Inspired by social learning algorithms, which require prior knowledge of the observations distribution, we propose a Social Machine Learning (SML) paradigm that is able to exploit the imperfect models generated during the learning phase. We show that this strategy results in consistent learning with high probability, and it yields a robust structure against poorly trained classifiers. Simulations with an ensemble of feedforward neural networks are provided to illustrate the theoretical results.


page 1

page 2

page 3

page 4


Learning from Heterogeneous Data Based on Social Interactions over Graphs

This work proposes a decentralized architecture, where individual agents...

Non-Asymptotic Performance of Social Machine Learning Under Limited Data

This paper studies the probability of error associated with the social m...

Optimal Linear Combination of Classifiers

The question of whether to use one classifier or a combination of classi...

Exploring the Universality of Hadronic Jet Classification

The modeling of jet substructure significantly differs between Parton Sh...

Theoretical Foundation of Co-Training and Disagreement-Based Algorithms

Disagreement-based approaches generate multiple classifiers and exploit ...

Network Classifiers With Output Smoothing

This work introduces two strategies for training network classifiers wit...

Blind Multi-class Ensemble Learning with Unequally Reliable Classifiers

The rising interest in pattern recognition and data analytics has spurre...

Please sign up or login with your details

Forgot password? Click here to reset