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
UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
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}.
Forward citations
Cited by 8 Pith papers
-
Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets
Introduces Hypergraph U-Nets with PHPool and PHUnpool operators derived from hierarchical clustering dendrograms for hypergraph reconstruction, classification, and anomaly detection.
-
Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning
Ev-DTAD improves event-based object detection accuracy and speed by using hierarchical temporal aggregation at the representation level and frequency-aware hypergraph fusion at the model level.
-
Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation
HyperNSD models hypergraph node states as an incidence-aware SDE whose pathwise variability yields competitive uncertainty estimates for OOD and misclassification detection.
-
EHHN: An Event-driven Heterogeneous Hypergraph Network for Object-Centric Next Activity Prediction
EHHN is a heterogeneous hypergraph network with dual micro-spatial and macro-evolution streams that achieves top accuracy and F1 on four OCEL benchmarks while cutting GPU memory use by up to 24x versus graph baselines.
-
Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural Networks
HADES adapts knowledge distillation for hypergraph neural networks by using quantified node heterophily as a proxy for teacher reliability, yielding student models that often outperform teachers with up to 12.3x faste...
-
Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning
Ev-DTAD introduces hierarchical temporal aggregation for event representation and frequency-aware hypergraph fusion for feature reasoning, delivering accuracy and speed gains on Gen1, 1Mpx/Gen4, and eTraM event detect...
-
Rethinking Event-Based Object Dtection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning
Ev-DTAD combines hierarchical temporal aggregation into a pseudo-RGB representation with frequency-aware hypergraph fusion to improve accuracy and speed in event-based object detection on Gen1, Gen4, and eTraM datasets.
-
Dynamic Hypergraph Representation Learning for Multivariate Time Series without Prior Knowledge
A pipeline uses community detection plus attention to create dynamic hypergraphs from raw multivariate time series and feeds them to DHACN for forecasting without prior structural knowledge
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.