International Conference on Computer and Knowledge Engineering

Home / 12th International Conference on Computer and Knowledge Engineering

AVID: A VARIATIONAL INFERENCE DELIBERATION FOR META-LEARNING

Authors :

Alireza Javaheri¹ Arsham Gholamzadeh Khoee² Saeed Reza Kheradpisheh³ Hadi Farahani⁴ Mohammad Ganjtabesh⁵

1- Department of Computer Sciences, Shahid Beheshti University, G.C., Tehran, Iran 2- Department of Computer Science, School of Mathematics, Statistics, and Computer Science, University of Tehran, Tehran, Iran 3- Department of Computer Sciences, Shahid Beheshti University, G.C., Tehran, Iran 4- Department of Computer Sciences, Shahid Beheshti University, G.C., Tehran, Iran 5- Department of Computer Science, School of Mathematics, Statistics, and Computer Science, University of Tehran, Tehran, Iran

Keywords :

Machine Learning،Meta-Learning،Few-shot Learning،Deep Learning،Variational Inference،Bayesian Methods

Abstract :

Meta-learning techniques enable quick learning of new tasks by using few samples with utilizing prior knowledge learned from previous tasks. Gradient-based models are widely used because of their simplicity and ability to solve a wide range of problems. However, they only succeed in solving tasks with a very similar structure since they adapt the model with a shared meta-parameter across all tasks. In recent years, some models have been proposed to enhance the gradient-based models to deal with task uncertainty and heterogeneity via sharing knowledge among similar tasks by using task clustering. Nevertheless, the high-dimensional parameter space of gradient-based models hinders them from achieving their full potential in low-data regimes. Bayesian meta-learning algorithms address this issue by learning a data-dependent latent generative representation of model parameters. Our proposed model bypasses the aforementioned limitations by leveraging Bayesian algorithms as well as clustering input tasks. The final analysis demonstrates the effectiveness of the proposed model for few-shot image classification problems.