Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

TL;DR

This paper introduces A2T, an attentive deep architecture that enables selective and adaptive transfer from multiple source tasks, effectively avoiding negative transfer and improving learning in the same domain.

Contribution

The paper presents a novel A2T architecture that adaptively transfers from multiple sources, addressing negative transfer and selective transfer in deep learning.

Findings

A2T effectively avoids negative transfer.

A2T selectively transfers from multiple sources.

Empirical results show improved learning performance.

Abstract

Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampers or slows down the learning instead of helping it. Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task. We propose A2T (Attend, Adapt and Transfer), an attentive deep architecture which adapts and transfers from these source tasks. Our model is generic enough to effect transfer of either policies or value functions. Empirical evaluations on different learning algorithms show that A2T is an effective architecture for transfer by being able to avoid negative transfer while transferring selectively from multiple source tasks in the same domain.