HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
This work addresses the problem of efficient and accurate graph learning for applications in domains like neuromorphic computing, though it appears incremental as it hybridizes existing techniques.
The authors tackled graph transductive learning by combining graph convolution with hyperdimensional computing, resulting in a method that is 9561 times faster than GCNII and 144.5 times faster than HDGL while outperforming them in accuracy on homophilic and heterophilic graphs.
We present a novel algorithm, \hdgc, that marries graph convolution with binding and bundling operations in hyperdimensional computing for transductive graph learning. For prediction accuracy \hdgc outperforms major and popular graph neural network implementations as well as state-of-the-art hyperdimensional computing implementations for a collection of homophilic graphs and heterophilic graphs. Compared with the most accurate learning methodologies we have tested, on the same target GPU platform, \hdgc is on average 9561.0 and 144.5 times faster than \gcnii, a graph neural network implementation and HDGL, a hyperdimensional computing implementation, respectively. As the majority of the learning operates on binary vectors, we expect outstanding energy performance of \hdgc on neuromorphic and emerging process-in-memory devices.