Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
This addresses the problem of efficient and interpretable hypergraph learning for researchers and practitioners, though it is incremental as it builds on linearized HNNs.
The paper tackles few-shot node classification on hypergraphs by proposing ZEN, a parameter-free hypergraph neural network that avoids overfitting and scalability issues, achieving up to 696x speedups and outperforming eight baselines in accuracy on 11 benchmarks.
Few-shot node classification on hypergraphs requires models that generalize from scarce labels while capturing high-order structures. Existing hypergraph neural networks (HNNs) effectively encode such structures but often suffer from overfitting and scalability issues due to complex, black-box architectures. In this work, we propose ZEN (Zero-Parameter Hypergraph Neural Network), a fully linear and parameter-free model that achieves both expressiveness and efficiency. Built upon a unified formulation of linearized HNNs, ZEN introduces a tractable closed-form solution for the weight matrix and a redundancy-aware propagation scheme to avoid iterative training and to eliminate redundant self information. On 11 real-world hypergraph benchmarks, ZEN consistently outperforms eight baseline models in classification accuracy while achieving up to 696x speedups over the fastest competitor. Moreover, the decision process of ZEN is fully interpretable, providing insights into the characteristic of a dataset. Our code and datasets are fully available at https://github.com/chaewoonbae/ZEN.