Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification

2025-10-24

AI Summary

To address the limited higher-order structural modeling and poor generalization in few-shot hypergraph node classification, this paper proposes ZEN—the first parameter-free, fully linear hypergraph neural network. Methodologically, ZEN (1) computes the weight matrix in closed form, eliminating iterative training entirely, and (2) introduces a redundancy-aware propagation mechanism that filters spurious higher-order information while preserving linear time complexity. The model is fully interpretable, inference-efficient, and inherently immune to overfitting. Evaluated on 11 real-world hypergraph datasets, ZEN consistently outperforms eight strong baselines, achieving the highest average classification accuracy and up to 696× faster single-inference speed. These results significantly advance the practicality and scalability of few-shot hypergraph learning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Addresses few-shot node classification on hypergraphs with scarce labels
• Solves overfitting and scalability in hypergraph neural networks
• Provides interpretable decision processes for hypergraph datasets

Innovation

• Parameter-free hypergraph neural network for few-shot learning
• Closed-form weight matrix solution eliminates iterative training
• Interpretable decision process with redundancy-aware propagation scheme