Hierarchical Information Fusion Graph Neural Networks for Chinese Implicit Rhetorical Questions Recognition

Li, Xiang; Qian, Zhong; Li, Peifeng; Zhu, Xiaofan

doi:10.1109/ijcnn55064.2022.9892514

Cited by 11 publications

(39 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The maximum accuracies demonstrated by our own implementation and those reported in other papers are shown in bold. The rows marked with "*" indicate the accuracies from papers [16], [37], [40], [41]. Figure 5 shows the optimal parameter settings used in MSI-H2GCN-2, which exhibited the highest average accuracy, as shown in Table 2.…”

Section: Resultsmentioning

confidence: 99%

Multi-Duplicated Characterization of Graph Structures Using Information Gain Ratio for Graph Neural Networks

Yuga

Kaneiwa

2023

IEEE Access

View full text Add to dashboard Cite

Various graph neural networks (GNNs) have been proposed to solve node classification tasks in machine learning for graph data. GNNs use the structural information of graph data by aggregating the feature vectors of neighboring nodes. However, they fail to directly characterize and leverage the structural information. In this paper, we propose a multi-duplicated characterization of graph structures using information gain ratio (IGR) for GNNs (MSI-GNN), which enhances the performance of node classification by using an i-hop adjacency matrix as the structural information of the graph data. In MSI-GNN, the i-hop adjacency matrix is adaptively adjusted by two methods: (i) structural features in the matrix are selected based on the information gain ratio and occurrence filter, and (ii) the selected features in (i) for each node are duplicated and combined flexibly. In an experiment, we show that our MSI-GNN outperforms GCN, H2GCN, and GCNII in terms of average accuracies in benchmark graph datasets.INDEX TERMS Graph neural networks (GNNs), machine learning, node classification, feature selection.

show abstract

Section: Resultsmentioning

confidence: 99%

Multi-Duplicated Characterization of Graph Structures Using Information Gain Ratio for Graph Neural Networks

Yuga

Kaneiwa

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Many models under consideration have their specific hyperparameters. We have fixed them to the values set for the squirrel dataset in all cases except for the GloGNN model (Li et al, 2022), which turned out to be very sensitive to its specific hyperparameters. Models are trained for the same number of steps as in the original papers, and we use early stopping on the validation set with the patience of 100 steps to prevent overfitting.…”

Section: Discussionmentioning

confidence: 99%

“…As for heterophilous graphs, the datasets used in most studies dedicated to learning under heterophily are limited to the six graphs adopted by Pei et al (2020): squirrel, chameleon, actor, texas, cornell, and wisconsin. These graphs have become the de-facto standard benchmark for evaluating heterophily-specific models and were used in numerous papers (Zhu et al, 2021;Chien et al, 2021;Yan et al, 2022;Maurya et al, 2022;Li et al, 2022;Wang & Zhang, 2022;Du et al, 2022;Suresh et al, 2021;Bo et al, 2021;Luan et al, 2022;Bodnar et al, 2022). We further discuss these datasets in Section 3.…”

Section: Graph Datasetsmentioning

confidence: 99%

“…Maurya et al (2022) proposed FSGNN which decouples feature aggregation from GNN layers and uses soft feature selection. Li et al (2022) developed GloGNN and GloGNN++ models that aggregate information from global nodes in the graph. proposed blockmodeling guided GNN architecture that can learn different aggregation rules for different nodes.…”

Section: Graph Datasetsmentioning

confidence: 99%

“…Heterophily-specific models We use eight models designed for node classification under heterophily: H 2 GCN (Zhu et al, 2020), CPGNN (Zhu et al, 2021), GPR-GNN (Chien et al, 2021), FSGNN (Maurya et al, 2022), GloGNN (Li et al, 2022), FAGCN (Bo et al, 2021), GBK- GNN (Du et al, 2022), and JacobiConv (Wang & Zhang, 2022). To the best of our knowledge, this is the most extensive comparison of heterophily-specific models in the literature.…”

Section: Setupmentioning

confidence: 99%

See 2 more Smart Citations

A critical look at the evaluation of GNNs under heterophily: are we really making progress?

Platonov¹,

Kuznedelev²,

Diskin³

et al. 2023

Preprint

View full text Add to dashboard Cite

Node classification is a classical graph representation learning task on which Graph Neural Networks (GNNs) have recently achieved strong results. However, it is often believed that standard GNNs only work well for homophilous graphs, i.e., graphs where edges tend to connect nodes of the same class. Graphs without this property are called heterophilous, and it is typically assumed that specialized methods are required to achieve strong performance on such graphs. In this work, we challenge this assumption. First, we show that the standard datasets used for evaluating heterophily-specific models have serious drawbacks, making results obtained by using them unreliable. The most significant of these drawbacks is the presence of a large number of duplicate nodes in the datasets squirrel and chameleon, which leads to train-test data leakage. We show that removing duplicate nodes strongly affects GNN performance on these datasets. Then, we propose a set of heterophilous graphs of varying properties that we believe can serve as a better benchmark for evaluating the performance of GNNs under heterophily. We show that standard GNNs achieve strong results on these heterophilous graphs, almost always outperforming specialized models. Our datasets and the code for reproducing our experiments are available at https://github.com/yandex-research/heterophilous-graphs.

show abstract

Contrastive graph clustering with adaptive filter

Xie

Chen

Kang

et al. 2023

Expert Systems with Applications

View full text Add to dashboard Cite

Hierarchical Information Fusion Graph Neural Networks for Chinese Implicit Rhetorical Questions Recognition

Cited by 11 publications

References 13 publications

Multi-Duplicated Characterization of Graph Structures Using Information Gain Ratio for Graph Neural Networks

Multi-Duplicated Characterization of Graph Structures Using Information Gain Ratio for Graph Neural Networks

A critical look at the evaluation of GNNs under heterophily: are we really making progress?

Contrastive graph clustering with adaptive filter

Contact Info

Product

Resources

About