Lifelong Teacher-Student Network Learning

TL;DR

This paper introduces a lifelong learning framework using a Teacher-Student network where the Teacher, a GAN, preserves past knowledge, and the Student, a VAE, learns from new data while retaining previous information across various training modes.

Contribution

It presents a novel lifelong learning approach employing a GAN-based Teacher and a VAE-based Student to retain and transfer knowledge across tasks.

Findings

Effective in supervised, semi-supervised, and unsupervised learning.

Preserves past knowledge using GAN-generated replay.

Captures both continuous and discrete data representations.

Abstract

A unique cognitive capability of humans consists in their ability to acquire new knowledge and skills from a sequence of experiences. Meanwhile, artificial intelligence systems are good at learning only the last given task without being able to remember the databases learnt in the past. We propose a novel lifelong learning methodology by employing a Teacher-Student network framework. While the Student module is trained with a new given database, the Teacher module would remind the Student about the information learnt in the past. The Teacher, implemented by a Generative Adversarial Network (GAN), is trained to preserve and replay past knowledge corresponding to the probabilistic representations of previously learn databases. Meanwhile, the Student module is implemented by a Variational Autoencoder (VAE) which infers its latent variable representation from both the output of the Teacher module as well as from the newly available database. Moreover, the Student module is trained to capture both continuous and discrete underlying data representations across different domains. The proposed lifelong learning framework is applied in supervised, semi-supervised and unsupervised training. The code is available~: \url{https://github.com/dtuzi123/Lifelong-Teacher-Student-Network-Learning}