Pith. sign in

REVIEW 8 cited by

UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.00956 v1 pith:JVCQOTI4 submitted 2021-05-03 cs.LG cs.SI

classification cs.LGcs.SI
keywords unignngraphhypergraphsframeworkhypergraphnetworksneuralgnns
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4\% to 88.8\% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at \url{https://github.com/OneForward/UniGNN}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation

    cs.LG 2026-07 conditional novelty 6.5 of 10

    HyperNSD models hypergraph node states as an incidence-aware SDE whose pathwise variability yields competitive uncertainty estimates for OOD and misclassification detection.

  2. Towards Trustworthy Hypergraph Neural Networks under Label Noise

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A benchmark and a robust framework, HyperTrust, showing that entropy-based hyperedge trustworthiness with selective edge boosting and pruning improves hypergraph node classification under label noise.

  3. Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphs

    cs.SI 2025-06 conditional novelty 6.0 of 10

    RASH learns relation importance from a dual heterogeneous hypergraph, constructs homophilic and heterophilic views, and uses contrastive learning to improve heterogeneous graph representations.

  4. Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A survey of n-ary knowledge representation learning methods proposes a two-dimensional taxonomy based on modeling technique and entity role/position awareness.

  5. Enhancing the Utility of Higher-Order Information in Relational Learning

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Graph-level GNNs with new hypergraph-based encodings beat hypergraph-specific GNNs on several benchmarks, and the encodings provably increase expressivity beyond graph-level encodings.

  6. From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Hypergraph diffusion provably collapses node representations, and a reaction term that exactly cancels diffusion dissipation keeps a designed transverse energy level nonzero in Hypergraph Neural Reaction–Diffusion (HNRD).

  7. Multi-view Fake News Detection Model Based on Dynamic Hypergraph

    cs.LG 2024-12 conditional novelty 5.0 of 10

    DHy-MFND learns news embeddings from text, propagation trees, and a dynamically refined hypergraph, and reports state-of-the-art accuracy on PolitiFact and Gossipcop.

  8. Computing and Learning on Combinatorial Data

    cs.AI 2025-02 conditional novelty 4.0 of 10

    A dissertation compiling five prior papers: GPU-accelerated persistent homology (HYPHA, Ripser++), near-linear-time approximated Wasserstein distance for persistence diagrams (PDoptFlow), and topology-based graph and ...

Pith tools