🤖 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.
📝 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.