Equivariant Hypergraph Neural Networks

Kim, Jin-Woo; Oh, Saeyoon; Cho, Sungjun; Hong, Seunghoon

doi:10.1007/978-3-031-19803-8_6

Cited by 5 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[24] also recently proposes efficient equivariant graph neural networks that can easily scale to higher-dimensional spaces. In addition, a permutation-equivariant network is proposed in [13] to capture both global and channel-wise contextual information. In [26], to build an equivariant network, orthogonal moments of the function are used as an effective means for encoding global invariance with respect to rotation and translation in fully-connected layers of the network.…”

Section: Related Workmentioning

confidence: 99%

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold

Shamsolmoali

Zareapoor

2023

2023 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

This paper focuses on an accurate and fast interpolation approach for image transformation employed in the design of CNN architectures. Standard Spatial Transformer Networks (STNs) use bilinear or linear interpolation as their interpolation, with unrealistic assumptions about the underlying data distributions, which leads to poor performance under scale variations. Moreover, STNs do not preserve the norm of gradients in propagation due to their dependency on sparse neighboring pixels. To address this problem, a novel Entropy STN (ESTN) is proposed that interpolates on the data manifold distributions. In particular, random samples are generated for each pixel in association with the tangent space of the data manifold and construct a linear approximation of their intensity values with an entropy regularizer to compute the transformer parameters. A simple yet effective technique is also proposed to normalize the nonzero values of the convolution operation, to fine-tune the layers for gradients' norm-regularization during training. Experiments on challenging benchmarks show that the proposed ESTN can improve predictive accuracy over a range of computer vision tasks, including image reconstruction, and classification, while reducing the computational cost.

show abstract

Section: Related Workmentioning

confidence: 99%

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold

Shamsolmoali

Zareapoor

2023

2023 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…It designs a hyperedge convolution operation to leverage the high-order correlations across data. Since then, a variety of hypergraph neural networks have been proposed for different learning tasks, including but not limited to image retrieval (Zeng et al 2023), quadratic assignment problem (Wang, Yan, and Yang 2021), biomedical science (Klimm, Deane, and Reinert 2021;Saifuddin et al 2022), keypoint matching (Kim et al 2022) and node classification (Bai, Zhang, and Torr 2021;Gao et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Hypergraph Neural Architecture Search

Lin,

Peng,

et al. 2024

AAAI

View full text Add to dashboard Cite

In recent years, Hypergraph Neural Networks (HGNNs) have achieved considerable success by manually designing architectures, which are capable of extracting effective patterns with high-order interactions from non-Euclidean data. However, such mechanism is extremely inefficient, demanding tremendous human efforts to tune diverse model parameters. In this paper, we propose a novel Hypergraph Neural Architecture Search (HyperNAS) to automatically design the optimal HGNNs. The proposed model constructs a search space suitable for hypergraphs, and derives hypergraph architectures through differentiable search strategies. A hypergraph structure-aware distance criterion is introduced as a guideline for obtaining an optimal hypergraph architecture via the leave-one-out method. Experimental results for node classification on benchmark Cora, Citeseer, Pubmed citation networks and hypergraph datasets show that HyperNAS outperforms existing HGNNs models and graph NAS methods.

show abstract

Hypercore decomposition for non-fragile hyperedges: concepts, algorithms, observations, and applications

Lee

Shin

2023

Data Min Knowl Disc

View full text Add to dashboard Cite

Equivariant Hypergraph Neural Networks

Cited by 5 publications

References 28 publications

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold

Hypergraph Neural Architecture Search

Hypercore decomposition for non-fragile hyperedges: concepts, algorithms, observations, and applications

Contact Info

Product

Resources

About