Graph Knowledge Distillation to Mixture of Experts
This addresses the problem of inconsistent performance in knowledge distillation for graph-based tasks, offering a domain-specific improvement for deploying efficient models.
The paper tackles the latency issue in Graph Neural Networks (GNNs) for node classification by proposing a knowledge distillation approach to a Mixture-of-Experts model called Routing-by-Memory, which achieves more consistent performance across datasets compared to existing methods.
In terms of accuracy, Graph Neural Networks (GNNs) are the best architectural choice for the node classification task. Their drawback in real-world deployment is the latency that emerges from the neighbourhood processing operation. One solution to the latency issue is to perform knowledge distillation from a trained GNN to a Multi-Layer Perceptron (MLP), where the MLP processes only the features of the node being classified (and possibly some pre-computed structural information). However, the performance of such MLPs in both transductive and inductive settings remains inconsistent for existing knowledge distillation techniques. We propose to address the performance concerns by using a specially-designed student model instead of an MLP. Our model, named Routing-by-Memory (RbM), is a form of Mixture-of-Experts (MoE), with a design that enforces expert specialization. By encouraging each expert to specialize on a certain region on the hidden representation space, we demonstrate experimentally that it is possible to derive considerably more consistent performance across multiple datasets. Code available at https://github.com/Rufaim/routing-by-memory.