On consequences of finetuning on data with highly discriminative features

Published: 02 Nov 2023, Last Modified: 18 Dec 2023UniReps PosterEveryoneRevisionsBibTeX
Keywords: finetuning, hidden represntations, transfer learning
Abstract: In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational resources. While its advantages are well-documented, we uncover a notable drawback: networks tend to prioritize basic data patterns, forsaking valuable pre-learned features. We term this behavior "feature erosion" and analyze its impact on network performance and internal representations.
Track: Extended Abstract Track
Submission Number: 54