Edge Sparsification for Graphs via Meta-Learning
Guihong Wan, Haim Schweitzer · 2021
We present a novel edge sparsification approach for semi-supervised learning on undirected and attributed graphs. The main challenge is to retain few edges while minimizing the loss of node classification accuracy. The task can be mathematically formulated as a bi-level optimization problem. We propose to use meta-gradients, which have traditionally been used in meta-learning, to solve the optimization problem, specifically, treating the graph adjacency matrix as hyperparameters to optimize. Experimental results show the effectiveness of the proposed approach. Remarkably, with the resulting sparse and light graph, in many cases the classification accuracy is significantly improved.