LGSep 20, 2022

MAC: A Meta-Learning Approach for Feature Learning and Recombination

arXiv:2209.09613v23 citationsh-index: 7
Originality Incremental advance
AI Analysis

This work addresses the challenge of feature adaptation in meta-learning for non-similar tasks, representing an incremental advance over existing methods like ANIL.

The paper tackles the problem of meta-learning for tasks from non-similar distributions by proposing MAC, a method that adds extra computational units to enable learning new features during meta-testing, resulting in a 13% performance improvement over ANIL in 5-shot settings.

Optimization-based meta-learning aims to learn an initialization so that a new unseen task can be learned within a few gradient updates. Model Agnostic Meta-Learning (MAML) is a benchmark algorithm comprising two optimization loops. The inner loop is dedicated to learning a new task and the outer loop leads to meta-initialization. However, ANIL (almost no inner loop) algorithm shows that feature reuse is an alternative to rapid learning in MAML. Thus, the meta-initialization phase makes MAML primed for feature reuse and obviates the need for rapid learning. Contrary to ANIL, we hypothesize that there may be a need to learn new features during meta-testing. A new unseen task from non-similar distribution would necessitate rapid learning in addition reuse and recombination of existing features. In this paper, we invoke the width-depth duality of neural networks, wherein, we increase the width of the network by adding extra computational units (ACU). The ACUs enable the learning of new atomic features in the meta-testing task, and the associated increased width facilitates information propagation in the forwarding pass. The newly learnt features combine with existing features in the last layer for meta-learning. Experimental results show that our proposed MAC method outperformed existing ANIL algorithm for non-similar task distribution by approximately 13% (5-shot task setting)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes