Single Model Ensemble using Pseudo-Tags and Distinct Vectors
This addresses the problem of high resource costs in model ensembles for machine learning practitioners, offering a more efficient alternative.
The paper tackles the computational inefficiency of model ensembles by proposing a single-model method using pseudo-tags and distinct vectors to replicate ensemble effects, achieving performance comparable to or better than traditional ensembles with 1/K-times fewer parameters.
Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort. In this study, we propose a novel method that replicates the effects of a model ensemble with a single model. Our approach creates K-virtual models within a single parameter space using K-distinct pseudo-tags and K-distinct vectors. Experiments on text classification and sequence labeling tasks on several datasets demonstrate that our method emulates or outperforms a traditional model ensemble with 1/K-times fewer parameters.