ModReduce: A Multi-Knowledge Distillation Framework with Online Learning

Yahya Saad Abbas, Abdelhakim Walid Badawy, Mohamed Mahfouz Shahawy, Samah Hussien, Samah Ayman, Hesham Mohamed Eraqi, Cherif Salama

Keywords: Knowledge distillation, Deep neural networks, Model Compression, Knowledge transfer, Online Learning

Abstract:

Deep neural networks have produced revolutionary results in many applications; however, the computational resources required to use such models are expensive in terms of processing power and memory space. Research has been conducted in the field of knowledge distillation, aiming to enhance the performance of smaller models. Knowledge distillation transfers knowledge from large networks into smaller ones. Literature defines three types of knowledge that can be transferred: response-based, relational-based, and feature-based.
To the best of our knowledge, only transferring one or two types of knowledge has been studied before, but transferring all three remains unexplored. In this paper, we propose ModReduce, a framework designed to transfer the three knowledge types in a unified manner using a combination of offline and online knowledge distillation. Moreover, an extensive experimental study on the effects of combining different knowledge types on student models’ generalization and overall performance has been performed. Our experiments showed that ModReduce outperforms state-of-the-art knowledge distillation methods in terms of Average Relative Improvement.

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