HGNN<sup>+</sup>: General Hypergraph Neural Networks

Gao, Yue; Feng, Yifan; Ji, Shuyi; Ji, Rongrong

doi:10.1109/tpami.2022.3182052

Cited by 152 publications

(43 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results are shown in Table 3. The results, shown in Table 3, demonstrate that HGIB consistently outperforms the previous state-of-the-art HGNN+ [8] in both scenarios, indicating that HGIB enhances the model's robustness for structure and feature perturbations, supporting its effectiveness for generalization and robustness.…”

Section: Resultsmentioning

confidence: 80%

“…DHGNN [12] exploits dynamically updating hypergraph structure on each layer. While HGNN+ [8] is an extended version of HGNN which is a general high-order multimodal data correlation modelling framework. We report the quantitative comparison of our technique vs. existing techniques in Table 1.…”

Section: Resultsmentioning

confidence: 99%

“…1(b). We then employ a neighbor strategy in feature space to generate the hyperedge groups following the same protocol as described in [8]. Specifically, for each vertex, its k-nearest neighbors in the feature space are connected by a hyperedge, resulting in the set of hyperedges Hypergraph Convolution.…”

Section: Hypergraph Modelling and Hypergraph Convolutionmentioning

confidence: 99%

“…Specifically, for each vertex, its k-nearest neighbors in the feature space are connected by a hyperedge, resulting in the set of hyperedges Hypergraph Convolution. We use spatial hypergraph convolution layers [8] for message aggregation. Messages can be passed either from vertex to hyperedge or from hyperedge to vertex using hyperpaths P , which is defined as…”

Section: Hypergraph Modelling and Hypergraph Convolutionmentioning

confidence: 99%

See 3 more Smart Citations

HGIB: Prognosis for Alzheimer's Disease via Hypergraph Information Bottleneck

Wang¹,

Avilés-Rivero²,

Kourtzi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Alzheimer's disease prognosis is critical for early Mild Cognitive Impairment patients for timely treatment to improve the patient's quality of life. Whilst existing prognosis techniques demonstrate potential results, they are highly limited in terms of using a single modality. Most importantly, they fail in considering a key element for prognosis: not all features extracted at the current moment may contribute to the prognosis prediction several years later. To address the current drawbacks of the literature, we propose a novel hypergraph framework based on an information bottleneck strategy (HGIB). Firstly, our framework seeks to discriminate irrelevant information, and therefore, solely focus on harmonising relevant information for future MCI conversion prediction (e.g., two years later). Secondly, our model simultaneously accounts for multi-modal data based on imaging and non-imaging modalities. HGIB uses a hypergraph structure to represent the multi-modality data and accounts for various data modality types. Thirdly, the key of our model is based on a new optimisation scheme. It is based on modelling the principle of information bottleneck into loss functions that can be integrated into our hypergraph neural network. We demonstrate, through extensive experiments on ADNI, that our proposed HGIB framework outperforms existing state-of-the-art hypergraph neural networks for Alzheimer's disease prognosis. We showcase our model even under fewer labels. Finally, we further support the robustness and generalisation capabilities of our framework under both topological and feature perturbations.

show abstract

Section: Resultsmentioning

confidence: 80%

Section: Resultsmentioning

confidence: 99%

Section: Hypergraph Modelling and Hypergraph Convolutionmentioning

confidence: 99%

Section: Hypergraph Modelling and Hypergraph Convolutionmentioning

confidence: 99%

See 2 more Smart Citations

HGIB: Prognosis for Alzheimer's Disease via Hypergraph Information Bottleneck

Wang¹,

Avilés-Rivero²,

Kourtzi³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the hypergraph structure G = (V, E) where V = {𝑣 1 , ..., 𝑣 𝑛 } is the vertice set and E = {𝑒 1 , ..., 𝑒 𝑚 } is the hyperedge set, a hyperedge can connect arbitrary number of vertices simultaneously. Therefore, superior to the abstraction of GCN on the pairwise connections or the modeling of CNN on the local features, the HCGN can better describe the high-level relations [51], [52], which provides an effective solution for expressing the knowledge routing from different domains to the target predictions.…”

Section: E Knowledge Integration For Multi-domain Transfermentioning

confidence: 99%

Learning General-Purpose Representations for Cross-Domain Hyperspectral Images Classification with Small Samples

Gao

Xiong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Cross-domain classification with small samples is a more challenging and realistic experimental setup. Until now, few studies have focused on the problem of small-sample cross-domain classification between completely different hyperspectral images (HSIs) since they possess different land cover types and statistical characteristics. To this end, this paper proposes a general-purpose representation learning method for cross-domain HSI classification, aiming to enable the model to learn more general-purpose deep representations that can quickly adapt to different target domains with small samples. The core of this method is to propose a novel three-level distillation strategy to transfer knowledge from multiple models well-trained on source HSIs into a single distilled model at the channel-, feature- and logit-level simultaneously. The learned representations can be further fine-tuned with small samples and quickly adapt to new target HSIs and previously unseen classes. Specifically, to transfer and fuse knowledge from multiple-source domains into a single model simultaneously and solve the inconsistency of the number of bands in different HSIs, an extensible multi-task model, including the channel transformation module, the feature extraction module and the linear classification module, is designed. Only the feature extraction module is shared across different HSIs, while the other two modules are domain-specific. Furthermore, the typical episode-based learning strategy of the metric-based meta-learning is adopted in the whole learning process to further improve the generalization ability and data efficiency. Extensive experiments are conducted on six source HSIs and four target HSIs, and the results demonstrate that the proposed method outperforms the existing advanced methods in cross-domain HSI classification with small samples.

show abstract