Heterogeneous Graph Neural Network via Attribute Completion

Jin, Di; Huo, Cuiying; Liang, Cong; Yang, Liang

doi:10.1145/3442381.3449914

Cited by 118 publications

(33 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GTN [54], which generates new graph structures by identifying useful connections between unconnected nodes on the original graph, can learn effective node embeddings on the new graphs in an end-to-end fashion. HGNN-AC [55] based on reference 53 proposed a general framework for heterogeneous graph neural network via Attribute Completion, including pre-learning of topological embedding and attribute completion with attention mechanism. These heterogeneous graph neural network representation methods enhance the representation ability of nodes and provide a more practical idea for downstream tasks.…”

Section: Heterogeneous Graph Neural Networkmentioning

confidence: 99%

HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

et al. 2022

View full text Add to dashboard Cite

With the continuous enrichment of social network applications, such as TikTok, Weibo, Twitter, and others, social media have become an indispensable part of our lives. Web users can participate in their favorite events or pay attention to people they like. The “heterogeneous” influence between events and users can be effectively modeled, and users’ potential future behaviors can be predicted, so as to facilitate applications such as recommendations and online advertising. For example, a user’s favorite live streaming host (user) recommends certain products (event), can we predict whether the user will buy these products in the future? The majority of studies are based on a homogeneous graph neural network to model the influence between users. However, these studies ignore the impact of events on users in reality. For instance, when users purchase commodities through live streaming channels, in addition to the factors of the host, the commodity is also a key factor that influences the behavior of users. This study designs an influence prediction model based on a heterogeneous neural network HetInf. Specifically, we first constructed the heterogeneous social influence network according to the relationship between event nodes and user nodes, then sampled the user heterogeneous subgraph for each user, extracted the relevant node features, and finally predicted the probability of user behavior through the heterogeneous neural network model. We conducted comprehensive experiments on two large social network datasets. Furthermore, the experimental results show that HetInf is significantly superior to the previous homogeneous neural network methods.

show abstract

Section: Heterogeneous Graph Neural Networkmentioning

confidence: 99%

HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…use node attribute to construct a K-Nearest Neighbor (KNN) graph, thereby enhancing the model's learning ability without modifying the original graph topology in the graph learning process. At the same time, some studies use joint optimization of multiple highly related tasks to estimate the missing information in a single task Jin et al [2021aJin et al [ , 2020, others use pre-training Lu et al [2021a] to accelerate the learning process. In addition, self-supervised methods can be used as another competitive macro-level augmentation strategy.…”

Section: Macro-level Augmentation Strategiesmentioning

confidence: 99%

“…Experimental results indicate the effectiveness of the proposed method in link prediction and attribute completion tasks. HGNN-AC Jin et al [2021a] use graph attention mechanism to complete the missing attributes of nodes in heterogeneous graphs, avoiding using previous hand-crafted ways to solve this problem.…”

Section: Gal For Low-quality Datamentioning

confidence: 99%

Graph Augmentation Learning

Yu¹,

Huang²,

Dao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc. Numerous GAL methods have been proposed for graph-based applications such as social network analysis and traffic flow forecasting. However, the underlying reasons for the effectiveness of these GAL methods are still unclear. As a consequence, how to choose optimal graph augmentation strategy for a certain application scenario is still in black box. There is a lack of systematic, comprehensive, and experimentally validated guideline of GAL for scholars. Therefore, in this survey, we in-depth review GAL techniques from macro (graph), meso (subgraph), and micro (node/edge) levels. We further detailedly illustrate how GAL enhance the data quality and the model performance. The aggregation mechanism of augmentation strategies and graph learning models are also discussed by different application scenarios, i.e., data-specific, model-specific, and hybrid scenarios. To better show the outperformance of GAL, we experimentally validate the effectiveness and adaptability of different GAL strategies in different downstream tasks. Finally, we share our insights on several open issues of GAL, including heterogeneity, spatio-temporal dynamics, scalability, and generalization.

show abstract

“…Graph Convolutional Network (GCN) (Kipf and Welling 2017), which is famous for its effectiveness in graph representation learning, follows the principal learning mechanism where adjacency nodes attain similar representations through aggregating their neighboring information. The representations support subsequent downstream tasks such as node classification (Duvenaud et al 2015;Jin et al 2021a;He et al 2021;Hu et al 2019) and link prediction (Schlichtkrull et al 2018;Zhang and Chen 2018; Kipf and Welling 2016;Cao et al 2021).…”

Section: Introductionmentioning

confidence: 99%

Block Modeling-Guided Graph Convolutional Neural Networks

Liang

Liu

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modelling into the framework of GCN so that it can realize “block-guided classified aggregation”, and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modelling into the aggregation process, GCN is able to automatically aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets.

show abstract

Heterogeneous Graph Neural Network via Attribute Completion

Cited by 118 publications

References 20 publications

HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

HetInf: Social Influence Prediction With Heterogeneous Graph Neural Network

Graph Augmentation Learning

Block Modeling-Guided Graph Convolutional Neural Networks

Contact Info

Product

Resources

About