Heterogeneous Graph Masked Autoencoders Metapath-based Edge Reconstruction 为了捕获复杂图结构中所涉及的语义,本文设计了基于元路径的边缘重构策略,通过元路径来探索高阶关系,并对复杂图的结构信息进行编码。具体来说,屏蔽基于元路径的边缘会破坏节点之间的短期语义联系,迫使模型去寻找其他地方来预测被屏蔽的关系。因此,...
自动编码器可以被认为是Kramer提出的主成分分析的非线性泛化。它的主要作用是降维或者说是特征学习,这种方式允许我们使用数据本身来进行特征提取和训练,而不依赖于人工标签。 在面对许多异构图任务时,尤其是生…
Tian Y, Dong K, Zhang C, Zhang C, Chawla NV (2023) Heterogeneous graph masked autoencoders. In: Proceedings of the AAAI conference on artificial intelligence, vol. 37, pp 9997–10005 Chen M, Huang C, Xia L, Wei W, Xu Y, Luo R (2023) Heterogeneous graph contrastive learning for rec...
Recently, the masked autoencoder (MAE) has been shown to effectively pre-train Vision Transformers (ViT) to improve their representational capabilities. Methods: In this paper, we investigated a self-pre-training paradigm for serial SEM images with MAE to implement downstr...
Specifically, we first propose a heterogeneous graph generative learning enhanced contrastive paradigm. This paradigm includes: 1) A contrastive view augmentation strategy by using a masked autoencoder. 2) Position-aware and semantics-aware positive sample sampling strategy for generating hard negative ...
However, the limiting aspect of these approaches is that they are computationally-intractable graph optimization problems as the cost functions are tailored for each team discovery criteria and they are NP-hard. More recently, researchers have adopted neural architectures, such as autoencoders and ...
Masked autoencoders are scalable vision learners. In CVPR, pages 16000–16009, June 2022. [23] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016. [24] Geoffrey Hinton, Oriol Vinyal...
The first part encodes network-specific drug and target features from heterogeneous drug and gene/protein networks through sequential graph attention networks (GAT). The combined drug and target features (Fdt) are fed into the second part to learn the updated Fdt by the five transformer encoders....
MNGACDA [48] constructs a multimodal network using various information sources from drugs and circRNA, and then applies an inner product decoder based on the embedding representations of drugs and circRNA to predict their interaction scores. GATECDA [49] employs a graph attention autoencoder (GATE...
Graph Masked Autoencoder for Spatio-Temporal Graph Learning Effective spatio-temporal prediction frameworks play a crucial role in urban sensing applications, including traffic analysis, human mobility behavior mode... Q Zhang,H Wang,SM Yiu,... 被引量: 0发表: 2024年 ...