Heterogeneous Graph Masked Autoencoders

Tian, Yijun; Dong, Kaiwen; Zhang, Chunhui; Zhang, Chuxu; Chawla, Nitesh V.

doi:10.1609/aaai.v37i8.26192

Cited by 37 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although early generative methods lagged behind contrastive methods, the recently proposed GraphMAE (Hou et al 2022) has greatly improved the empirical performance of generative methods through sophisticated designs and triggered many subsequent studies, such as WGDN (Cheng et al 2023), SeeGera (Li et al 2023), and HGMAE (Tian et al 2023). However, the theoretical support of GraphMAE is still not thoroughly investigated.…”

Section: Related Workmentioning

confidence: 99%

Key Technology of Automation Control Based on Artificial Intelligence Technology

Wang

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure between local frames tends to be inaccurate due to the lack of guidance to force long-range temporal perception; ii) explicit motion learning is usually ignored, leading to partial information loss. To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder. Specifically, the long-short contrastive objective is to endow local frame features with long-form temporal awareness by maximizing their agreement with the global token of videos belonging to the same class. The motion autodecoder is a lightweight architecture to reconstruct pixel motions from the differential features, which explicitly embeds the network with motion dynamics. By this means, MoLo can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching. To demonstrate the effectiveness, we evaluate MoLo on five standard benchmarks, and the results show that MoLo favorably outperforms recent advanced methods. The source code is available at https://github. com/alibaba-mmai-research/MoLo.

show abstract

Section: Related Workmentioning

confidence: 99%

Key Technology of Automation Control Based on Artificial Intelligence Technology

Wang

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…data (Wang et al 2023;Tian et al 2023) due to the inherent non-independent and identically distributed (non-IID) nature of graphs. Therefore, a series of Federated Graph Learning (FGL) (Fu et al 2022;Liu and Yu 2022) methods have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Federated Graph Learning under Domain Shift with Generalizable Prototypes

Wan,

Huang,

2024

AAAI

View full text Add to dashboard Cite

Federated Graph Learning is a privacy-preserving collaborative approach for training a shared model on graph-structured data in the distributed environment. However, in real-world scenarios, the client graph data usually originate from diverse domains, this unavoidably hinders the generalization performance of the final global model. To address this challenge, we start the first attempt to investigate this scenario by learning a well-generalizable model. In order to improve the performance of the global model from different perspectives, we propose a novel framework called Federated Graph Learning with Generalizable Prototypes (FGGP). It decouples the global model into two levels and bridges them via prototypes. These prototypes, which are semantic centers derived from the feature extractor, can provide valuable classification information. At the classification model level, we innovatively eschew the traditional classifiers, then instead leverage clustered prototypes to capture fruitful domain information and enhance the discriminative capability of the classes, improving the performance of multi-domain predictions. Furthermore, at the feature extractor level, we go beyond traditional approaches by implicitly injecting distinct global knowledge and employing contrastive learning to obtain more powerful prototypes while enhancing the feature extractor generalization ability. Experimental results on various datasets are presented to validate the effectiveness of the proposed method.

show abstract

“…Accordingly, Graph Neural Networks (GNNs) [2,3], a powerful tool for mining graph data [4,5], have achieved exciting results in several tasks [6][7][8][9][10][11][12]. Recently, researchers have begun to investigate the potential of GNNs on heterogeneous graphs and design models that specifically deal with heterogeneous graphs, which are called heterogeneous graph neural networks (HGNNs) [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Multi-view Heterogeneous Graph Neural Networks for Node Classification

Zeng,

Lei,

Wang

et al. 2024

Data Sci. Eng.

View full text Add to dashboard Cite

Recently, with graph neural networks (GNNs) becoming a powerful technique for graph representation, many excellent GNN-based models have been proposed for processing heterogeneous graphs, which are termed Heterogeneous graph neural networks (HGNNs). However, existing HGNNs tend to aggregate information from either direct neighbors or those connected by short metapaths, thereby neglecting the higher-order information and global feature similarity information in heterogeneous graphs. In this paper, we propose a Multi-View Heterogeneous graph neural network (MV-HGNN) to aggregate these information. Firstly, two auxiliary views, specifically a global feature similarity view and a graph diffusion view, are generated from the original heterogeneous graph. Secondly, MV-HGNN performs two message-passing strategies to get the representation of different views. Subsequently, a transformer-based aggregator is used to get the semantic information. Subsequently, the representations of the three views are fused into a final composite representation. We evaluate our method on the node classification task over three commonly used heterogeneous graph datasets, and the results demonstrate that our proposed MV-HGNN significantly outperforms state-of-the-art baselines.

show abstract

Heterogeneous Graph Masked Autoencoders

Cited by 37 publications

References 30 publications

Key Technology of Automation Control Based on Artificial Intelligence Technology

Key Technology of Automation Control Based on Artificial Intelligence Technology

Federated Graph Learning under Domain Shift with Generalizable Prototypes

Multi-view Heterogeneous Graph Neural Networks for Node Classification

Contact Info

Product

Resources

About