Causal GraphSAGE: A robust graph method for classification based on causal sampling

Zhang, Tao; Shan, Haoran; Little, Max A.

doi:10.1016/j.patcog.2022.108696

Cited by 27 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods based on graph neural networks: Methods such as GCN [25,26], SGCN [27], GIN [14], and Causal GraphSAGE [28] aggregate information over neighboring nodes through convolution of multiple layers. These methods can capture the local structure of the nodes but have limitations in dealing with the global structure.…”

Section: Related Workmentioning

confidence: 99%

GraphSAGE++: Weighted Multi-scale GNN for Graph Representation Learning

Jiawei,

Zhang,

Yang

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

Graph neural networks (GNNs) have emerged as a powerful tool in graph representation learning. However, they are increasingly challenged by over-smoothing as network depth grows, compromising their ability to capture and represent complex graph structures. Additionally, some popular GNN variants only consider local neighbor information during node updating, ignoring the global structural information and leading to inadequate learning and differentiation of graph structures. To address these challenges, we introduce a novel graph neural network framework, GraphSAGE++. Our model extracts the representation of the target node at each layer and then concatenates all layer weighted representations to obtain the final result. In addition, the strategies combining double aggregations with weighted concatenation are proposed, which significantly enhance the model’s discernment and preservation of structural information. Empirical results on various datasets demonstrate that GraphSAGE++ excels in vertex classification, link prediction, and visualization tasks, surpassing existing methods in effectiveness.

show abstract

Section: Related Workmentioning

confidence: 99%

GraphSAGE++: Weighted Multi-scale GNN for Graph Representation Learning

Jiawei,

Zhang,

Yang

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…This approach captures the local neighborhood structure of the graph and has been shown to perform well on various graph-based machine learning tasks. Other popular graph embedding methods include Node2Vec [22], which is an extension of DeepWalk that balances between the breadth-first and depth-first search strategies during random walk, and GraphSAGE [23], which learns embeddings by aggregating feature information from a node's local neighborhood using a neural network.…”

Section: Graph Embeddingmentioning

confidence: 99%

Graph embedding approach to analyze sentiments on cryptocurrency

Moudhich,

Fennan

2024

IJECE

View full text Add to dashboard Cite

This paper presents a comprehensive exploration of graph embedding techniques for sentiment analysis. The objective of this study is to enhance the accuracy of sentiment analysis models by leveraging the rich contextual relationships between words in text data. We investigate the application of graph embedding in the context of sentiment analysis, focusing on it is effectiveness in capturing the semantic and syntactic information of text. By representing text as a graph and employing graph embedding techniques, we aim to extract meaningful insights and improve the performance of sentiment analysis models. To achieve our goal, we conduct a thorough comparison of graph embedding with traditional word embedding and simple embedding layers. Our experiments demonstrate that the graph embedding model outperforms these conventional models in terms of accuracy, highlighting it is potential for sentiment analysis tasks. Furthermore, we address two limitations of graph embedding techniques: handling out-of-vocabulary words and incorporating sentiment shift over time. The findings of this study emphasize the significance of graph embedding techniques in sentiment analysis, offering valuable insights into sentiment analysis within various domains. The results suggest that graph embedding can capture intricate relationships between words, enabling a more nuanced understanding of the sentiment expressed in text data.

show abstract

“…On the other hand, these models fail to consider inner relationships among features and thus suffer from the performance drop on the out-of-distribution data (Wu et al, 2022). In effect, causal inference endows the prediction with better model generalization and performance robustness (Zhang et al, 2022a).…”

Section: Introductionmentioning

confidence: 99%

“…The mechanism of GraphFwFM for feature graphGGNNs and other types of GNNs are prone to over-smoothing as the number of neural network layers increases(Zhou et al, 2020). As illustrated by previous research (e.g.,Little & Badawy, 2019;Guo et al, 2020;Zhang et al, 2022a), sampling based on causal relationships among features can increase the performance robustness of prediction models. In this research, we sample a node's neighbors in feature graph based on the causality-based weighted adjacency matrix learnt in Section 3.2.1.…”

mentioning

confidence: 99%