Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

Karsten Roth, Lukas Thede, A. Sophia Koepke, Oriol Vinyals, Olivier J Henaff, Zeynep Akata

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.

Keywords: transfer learning, pretraining, weak-to-strong transfer, continual learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We first show that transferable knowledge exists between any pairs of models pretrained on the same data. We then study and propose approaches to transfer this knowledge between any model pair - independent of relative performances & architectures.

Abstract: Training deep networks requires various design decisions regarding for instance their architecture, data augmentation, or optimization. In this work, we find these training variations to result in networks learning unique feature sets from the data. Using public model libraries comprising thousands of models trained on canonical datasets like ImageNet, we observe that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other – independent of overall performance. Given any arbitrary pairing of pretrained models and no external rankings (such as separate test sets, e.g. due to data privacy), we investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation – a task made particularly difficult as additional knowledge can be contained in stronger, equiperformant or weaker models. Yet facilitating robust transfer in scenarios agnostic to pretrained model pairings would unlock auxiliary gains and knowledge fusion from any model repository without restrictions on model and problem specifics - including from weaker, lower-performance models. This work therefore provides an initial, in-depth exploration on the viability of such general-purpose knowledge transfer. Across large-scale experiments, we first reveal the shortcomings of standard knowledge distillation techniques, and then propose a much more general extension through data partitioning for successful transfer between nearly all pretrained models, which we show can also be done unsupervised. Finally, we assess both the scalability and impact of fundamental model properties on successful model-agnostic knowledge transfer.

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.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 4151