Hyperdimensional Representation Learning for Node Classification and Link Prediction
This addresses graph learning problems for researchers and practitioners by offering a more efficient alternative to GNNs, though it is incremental as it builds on existing hyperdimensional computing and GNN concepts.
The paper tackles node classification and link prediction in graphs by introducing Hyperdimensional Graph Learner (HDGL), which maps node features into a high-dimensional space and uses operators like bundling and binding for aggregation, achieving competitive accuracy with state-of-the-art GNNs at reduced computational cost and matching DeepWalk's performance on link prediction.
We introduce Hyperdimensional Graph Learner (HDGL), a novel method for node classification and link prediction in graphs. HDGL maps node features into a very high-dimensional space (\textit{hyperdimensional} or HD space for short) using the \emph{injectivity} property of node representations in a family of Graph Neural Networks (GNNs) and then uses HD operators such as \textit{bundling} and \textit{binding} to aggregate information from the local neighborhood of each node yielding latent node representations that can support both node classification and link prediction tasks. HDGL, unlike GNNs that rely on computationally expensive iterative optimization and hyperparameter tuning, requires only a single pass through the data set. We report results of experiments using widely used benchmark datasets which demonstrate that, on the node classification task, HDGL achieves accuracy that is competitive with that of the state-of-the-art GNN methods at substantially reduced computational cost; and on the link prediction task, HDGL matches the performance of DeepWalk and related methods, although it falls short of computationally demanding state-of-the-art GNNs.