Towards Estimating Transferability using Hard Subsets

Tarun Ram Menta, Surgan Jandial, Akash Patil, Vimal K B, Saketh Bachu, Balaji Krishnamurthy, Vineeth N. Balasubramanian, Chirag Agarwal, Mausoom Sarkar

Keywords: Transfer Learning, Transferability, Hard Subsets

TL;DR: We propose HASTE, a strategy that ensures better transferability estimation using just a hard subset of target data.

Abstract: As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suitable for a given target task without performing computationally expensive fine-tuning. In this work, we propose HASTE (HArd Subset TransfErability), a new strategy to estimate the transferability of a source model to a particular target task using only a harder subset of target data. By leveraging the model’s internal and output representations, we introduce two techniques – one class-agnostic and another class-specific – to identify harder subsets and show that HASTE can be used with any existing transferability metric to improve their reliability. We further analyze the relation between HASTE and the optimal average log-likelihood as well as negative conditional entropy and empirically validate our theoretical bounds. Our experimental results across multiple source model architectures, target datasets, and transfer learning tasks show that HASTE-modified metrics are consistently better or on par with the state-of-the-art transferability metrics.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/towards-estimating-transferability-using-hard/code)