Pre-training on large-scale heterogeneous graph

Pre-training on large-scale heterogeneous graph

Graph neural networks (GNNs) emerge as the state-of-the-art representation learning methods on graphs and often rely on a large amount of labeled data to achieve satisfactory performance. Recently, in order to relieve the label scarcity issues, some works propose to pre-train GNNs in a self-supervis...

Saved in:

書目詳細資料
Main Authors:	JIANG, Xunqiang, JIA, Tianrui, FANG, Yuan, SHI, Chuan, LIN, Zhe, WANG, Hui
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2021
主題:	Heterogeneous graph Self-supervised learning Pre-training Databases and Information Systems
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/6888 https://ink.library.smu.edu.sg/context/sis_research/article/7891/viewcontent/KDD21_PT_HGNN.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Singapore Management University
語言:	English

相似書籍

Contrastive pre-training of GNNs on heterogeneous graphs
由: JIANG, Xunqiang, et al.
出版: (2021)

Learning to pre-train graph neural networks
由: LU, Yuanfu, et al.
出版: (2021)

Dynamic heterogeneous graph embedding via heterogeneous Hawkes process
由: JI, Yugang, et al.
出版: (2021)

Graphprompt: Unifying pre-training and downstream tasks for graph neural networks
由: LIU, Zemin, et al.
出版: (2023)

Accelerating large-scale heterogeneous interaction graph embedding learning via importance sampling
由: JI, Yugang, et al.
出版: (2021)

Learning on heterogeneous graphs using high-order relations
由: Lee, See Hian, et al.
出版: (2021)

SELF-SUPERVISED MODELING FOR MULTI-MODAL UNDERSTANDING
由: YUE XIANGHU
出版: (2024)

Augmenting low-resource text classification with graph-grounded pre-training and prompting
由: WEN, Zhihao, et al.
出版: (2023)

The 4th workshop on heterogeneous information network analysis and applications (HENA 2021)
由: SHI, Chuan, et al.
出版: (2021)

Masked autoencoders for contrastive learning of heterogenous graphs
由: Srinthi Nachiyar D/O Thangamuthu
出版: (2024)

Heterogeneous embedding propagation for large-scale e-commerce user alignment
由: ZHENG, Vincent W., et al.
出版: (2018)

Generalized graph prompt: Toward a unification of pre-training and downstream tasks on graphs
由: YU, Xingtong, et al.
出版: (2024)

Dynamic meta-path guided temporal heterogeneous graph neural networks
由: JI, Yugang, et al.
出版: (2024)

Pre-training graph transformer with multimodal side information for recommendation
由: Liu, Yong, et al.
出版: (2022)

Heterogeneous graph transformer with poly-tokenization
由: LU, Zhiyuan, et al.
出版: (2024)

Link prediction on latent heterogeneous graphs
由: NGUYEN, Trung Kien, et al.
出版: (2023)

Topic-aware heterogeneous graph neural network for link prediction
由: XU, Siyong, et al.
出版: (2021)

Metagraph-based learning on heterogeneous graphs
由: FANG, Yuan, et al.
出版: (2019)

Temporal heterogeneous interaction graph embedding for next-item recommendation
由: JI, Yugang, et al.
出版: (2020)

A graph theoretic approach for optimizing key pre-distribution in wireless sensor networks
由: Chan, A.C.-F.
出版: (2013)

When convolutional network meets temporal heterogeneous graphs: an effective community detection method
由: Zheng, Yaping, et al.
出版: (2023)

Voucher abuse detection with prompt-based fine-tuning on graph neural networks
由: WEN, Zhihao, et al.
出版: (2023)

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
由: FENG FULI, et al.
出版: (2020)

Heterogeneous graph neural network with multi-view representation learning
由: SHAO, Zezhi, et al.
出版: (2023)

Compressing pre-trained models of code into 3 MB
由: SHI, Jieke, et al.
出版: (2022)

Retrieval based code summarisation using code pre-trained models
由: Gupta, Sahaj
出版: (2024)

Approximate personalized propagation for unsupervised embedding in heterogeneous graphs
由: Chen, Yibi, et al.
出版: (2022)

MANDO-GURU: vulnerability detection for smart contract source code by heterogeneous graph embeddings
由: NGUYEN, Huu Hoang, et al.
出版: (2022)

Automated commit intelligence by pre-training
由: Liu, Shangqing, et al.
出版: (2025)

MANDO: Multi-level heterogeneous graph embeddings for fine-grained detection of smart contract vulnerabilities
由: NGUYEN, Huu Hoang, et al.
出版: (2022)

Natural attack for pre-trained models of code
由: YANG, Zhou, et al.
出版: (2022)

PTM4Tag: sharpening tag recommendation of stack overflow posts with pre-trained models
由: HE, Junda, et al.
出版: (2022)

On the transferability of pre-trained language models for low-resource programming languages
由: CHEN, Fuxiang, et al.
出版: (2022)

MANDO-HGT: Heterogeneous graph transformers for smart contract vulnerability detection
由: NGUYEN, Huu Hoang, et al.
出版: (2023)

PTM4Tag+: Tag recommendation of stack overflow posts with pre-trained models
由: HE, Junda, et al.
出版: (2025)

Iterative graph self-distillation
由: ZHANG, Hanlin, et al.
出版: (2024)

Prototypical graph contrastive learning
由: LIN, Shuai, et al.
出版: (2022)

Sentiment analysis for software engineering: How far can pre-trained transformer models go?
由: ZHANG, Ting, et al.
出版: (2020)

Subdivision number of large complete graphs and large complete multipartite graphs
由: Gervacio, Severino V.
出版: (2005)

Injecting descriptive meta-information into pre-trained language models with hypernetworks
由: DUAN, Wenying, et al.
出版: (2021)