Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network
This work addresses the need for more interpretable and effective knowledge transfer in light-weight neural networks, offering an incremental improvement over existing distillation techniques.
The paper tackles the problem of knowledge distillation by proposing interpretable embedding procedure knowledge based on principal component analysis and distilling it with a message passing neural network, resulting in a 2.28% improvement on CIFAR100 compared to state-of-the-art methods.
Knowledge distillation (KD) is one of the most useful techniques for light-weight neural networks. Although neural networks have a clear purpose of embedding datasets into the low-dimensional space, the existing knowledge was quite far from this purpose and provided only limited information. We argue that good knowledge should be able to interpret the embedding procedure. This paper proposes a method of generating interpretable embedding procedure (IEP) knowledge based on principal component analysis, and distilling it based on a message passing neural network. Experimental results show that the student network trained by the proposed KD method improves 2.28% in the CIFAR100 dataset, which is higher performance than the state-of-the-art (SOTA) method. We also demonstrate that the embedding procedure knowledge is interpretable via visualization of the proposed KD process. The implemented code is available at https://github.com/sseung0703/IEPKT.