An Efficient GNNs-to-KANs Distillation via Self-Attention Dynamic Sampling with Potential for Consumer Electronics Edge Deployment
This addresses model compression and speed for consumer electronics edge deployment, representing an incremental improvement in distillation methods.
The paper tackles the problem of deploying deep learning models on resource-constrained edge devices by proposing a knowledge distillation framework from Graph Neural Networks (GNNs) to Kolmogorov-Arnold Networks (KANs), achieving performance improvements of 3.05%-3.62% over GNN teachers and a 16.96x reduction in parameters with a 55.75% decrease in inference time.
Knowledge distillation (KD) is crucial for deploying deep learning models in resource-constrained edge environments, particularly within the consumer electronics sector, including smart home devices, wearable technology, and mobile terminals. These applications place higher demands on model compression and inference speed, necessitating the transfer of knowledge from Graph Neural Networks (GNNs) to more efficient Multi-Layer Perceptron (MLP) models. However, due to their fixed activation functions and fully connected architecture, MLPs face challenges in rapidly capturing the complex neighborhood dependencies learned by GNNs, thereby limiting their performance in edge environments. To address these limitations, this paper introduces an innovative from GNNs to Kolmogorov-Arnold Networks (KANs) knowledge distillation framework-Self Attention Dynamic Sampling Distillation (SA-DSD). This study improved Fourier KAN (FR-KAN) and replaced MLP with the improved FR-KAN+ as the student model. Through the incorporation of learnable frequency bases and phase-shift mechanisms, along with algorithmic optimization, FR-KAN significantly improves its nonlinear fitting capability while effectively reducing computational complexity. Building on this, a margin-level sampling probability matrix, based on teacher-student prediction consistency, is constructed, and an adaptive weighted loss mechanism is designed to mitigate performance degradation in the student model due to the lack of explicit neighborhood aggregation. Extensive experiments conducted on six real-world datasets demonstrate that SA-DSD achieves performance improvements of 3.05%-3.62% over three GNN teacher models and 15.61% over the FR-KAN+ model. Moreover, when compared with key benchmark models, SA-DSD achieves a 16.96x reduction in parameter count and a 55.75% decrease in inference time.