LGCLNov 6, 2016

Beyond Fine Tuning: A Modular Approach to Learning on Small Data

arXiv:1611.01714v115 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of limited data availability for machine learning practitioners, offering a more effective alternative to fine-tuning, though it appears incremental as it builds on existing transfer learning concepts.

The paper tackles the problem of training neural networks on small datasets by introducing a modular approach that combines pre-trained and untrained modules to learn distribution shifts, surpassing standard fine-tuning methods and significantly improving performance with less data.

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural network or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning. Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.

Foundations

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

Your Notes