SEGEN: Sample-Ensemble Genetic Evolutional Network Model
share
Deep learning, a rebranding of deep neural network research works, has achieved remarkable success in recent years. With multiple hidden layers, deep learning models aim at computing hierarchical features or representations of the observational data. Meanwhile, due to its severe disadvantages in data consumption, computational resources, parameter tuning efforts and the lack of result explainability, deep learning has also suffered from lots of criticism. In this paper, we will introduce a new representation learning model, namely "Sample-Ensemble Genetic Evolutional Network" (SEGEN), which can serve as an alternative approach to deep learning models. Instead of building one single deep model, based on a set of sampled sub-instances, SEGEN adopts a genetic-evolutional learning strategy to build a group of unit models generations by generations. The unit models incorporated in SEGEN can be either traditional machine learning models or the recent deep learning models with a much "smaller" and "shallower" architecture. The learning results of each instance at the final generation will be effectively combined from each unit model via diffusive propagation and ensemble learning strategies. From the computational perspective, SEGEN requires far less data, fewer computational resources and parameter tuning works, but has sound theoretic interpretability of the learning process and results. Extensive experiments have been done on real-world network structured datasets, and the experimental results obtained by SEGEN have demonstrate its advantages over the other state-of-the-art representation learning models.
READ FULL TEXT