Co-Representation Neural Hypergraph Diffusion for Edge-Dependent Node Classification

📅 2024-05-23
🏛️ arXiv.org
📈 Citations: 3
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses edge-dependent node classification (ENC), where a node may assume distinct labels across different hyperedges, necessitating joint modeling of node–edge pairs. Existing approaches—e.g., WHATsNet—suffer from entangled hyperedge features, non-adaptive representation dimensions, and over-smoothing. To overcome these limitations, we propose the first neuralized, differentiable diffusion framework that models node–edge co-representations as a hypergraph diffusion process. Our multi-input multi-output architecture unifies intra-hyperedge and intra-node interactions while enabling data-adaptive message aggregation. Evaluated on multiple real-world hypergraph benchmarks, our method achieves significant improvements over state-of-the-art methods in both accuracy and efficiency, demonstrating strong generalization—particularly for modeling high-order heterogeneous relational structures.

Technology Category

Application Category

📝 Abstract
Hypergraphs are widely employed to represent complex higher-order relations in real-world applications. Most hypergraph learning research focuses on node-level or edge-level tasks. A practically relevant but more challenging task, edge-dependent node classification (ENC), is only recently proposed. In ENC, a node can have different labels across different hyperedges, which requires the modeling of node-edge pairs instead of single nodes or hyperedges. Existing solutions for this task are based on message passing and model interactions in within-edge and within-node structures as multi-input single-output functions. This brings three limitations: (1) non-adaptive representation size, (2) non-adaptive messages, and (3) insufficient direct interactions among nodes or edges. To tackle these limitations, we propose CoNHD, a new ENC solution that models both within-edge and within-node interactions as multi-input multi-output functions. Specifically, we represent these interactions as a hypergraph diffusion process on node-edge co-representations. We further develop a neural implementation for this diffusion process, which can adapt to a specific ENC dataset. Extensive experiments demonstrate the effectiveness and efficiency of the proposed CoNHD method.
Problem

Research questions and friction points this paper is trying to address.

Addressing edge-dependent node classification where nodes have different labels across hyperedges
Solving entangled edge-specific features and non-adaptive representation sizes in hypergraph learning
Overcoming oversmoothing issues in existing hypergraph neural network architectures
Innovation

Methods, ideas, or system contributions that make the work stand out.

Models hypergraph diffusion using node-edge co-representations
Employs equivariant networks as diffusion operators
Addresses entangled features and oversmoothing in hypergraphs
🔎 Similar Papers
No similar papers found.
Y
Yijia Zheng
University of Amsterdam, Amsterdam, the Netherlands
M
M. Worring
University of Amsterdam, Amsterdam, the Netherlands