paper-with-me

Papers

GraphMAE: Self-Supervised Masked Graph Autoencoders

2022-05-22 · Zhenyu Hou, Xiao Liu, Yukuo Cen, Yuxiao Dong, Hongxia Yang, Chunjie Wang, Jie Tang

Self-supervised learning (SSL) has been extensively explored in recent years. Particularly, generative SSL has seen emerging success in natural language processing and other AI fields, such as the wide adoption of BERT and GPT. Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields. In this paper, we identify and examine the issues that negatively impact the development of GAEs, including their reconstruction objective, training robustness, and error metric. We present a masked graph autoencoder GraphMAE that mitigates these issues for generative self-supervised graph pretraining. Instead of reconstructing graph structures, we propose to focus on feature reconstruction with both a masking strategy and scaled cosine error that benefit the robust training of GraphMAE. We conduct extensive experiments on 21 public datasets for three different graph learning tasks. The results manifest that GraphMAE-a simple graph autoencoder with careful designs-can consistently generate outperformance over both contrastive and generative state-of-the-art baselines. This study provides an understanding of graph autoencoders and demonstrates the potential of generative self-supervised pre-training on graphs.

📄 PDF Abstract BibTeX arXiv:2205.10803

Code (3)

thudm/graphmae 공식 구현 pytorch
thudm/graphmae2 pytorch
wehos/cellt pytorch

Tasks

Contrastive LearningGraph ClassificationGraph LearningNode ClassificationRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

2023-04-10 · Zhenyu Hou, Yufei He, Yukuo Cen, Xiao Liu 외

Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data. Among both sets of graph SSL …

Self-Supervised Learning

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

2024-02-11 · Xiang Tao, Qiang Liu, Shu Wu, Liang Wang

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past…

Contrastive LearningSelf-Supervised Learning

CORE: Contrastive Masked Feature Reconstruction on Graphs

2025-12-15 · Jianyuan Bo, Yuan Fang arxiv

In the rapidly evolving field of self-supervised learning on graphs, generative and contrastive methodologies have emerged as two dominant approaches. Our study focuses on masked feature reconstruction (MFR), a generativ…

Self-Supervised LearningGraph ClassificationContrastive LearningNode Classification

Dual-branch PolSAR Image Classification Based on GraphMAE and Local Feature Extraction

2024-08-08 · Yuchen Wang, Ziyi Guo, Haixia Bi, Danfeng Hong 외

The annotation of polarimetric synthetic aperture radar (PolSAR) images is a labor-intensive and time-consuming process. Therefore, classifying PolSAR images with limited labels is a challenging task in remote sensing do…

Classificationimage-classificationImage ClassificationSelf-Supervised Learning

What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders

2022-05-20 · Jintang Li, Ruofan Wu, Wangbin Sun, Liang Chen 외

The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph auto…

Contrastive LearningLink PredictionNode ClassificationSelf-Supervised Learning