One-Shot Graph Representation Learning Using Hyperdimensional Computing

arXiv:2402.17073v1 Announce Type: new
Abstract: We present a novel, simple, fast, and efficient approach for semi-supervised learning on graphs. The proposed approach takes advantage of hyper-dimensional computing which encodes data samples using random projections into a high dimensional space (HD space for short). Specifically, we propose a Hyper-dimensional Graph Learning (HDGL) algorithm that leverages the injectivity property of the node representations of a family of graph neural networks. HDGL maps node features to the HD space and then uses HD …

abstract algorithm arxiv computing cs.ai cs.lg cs.si data graph graph learning graph representation graphs novel random representation representation learning samples semi-supervised semi-supervised learning simple space supervised learning type