Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification

2020-12-14 · Deli Chen, Yankai Lin, Lei LI, Xuancheng Ren, Peng Li, Jie zhou, Xu sun

Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC). However, existing GCL methods are generally transferred from other fields like CV or NLP, whose underlying working mechanism remains under-explored. In this work, we first deeply probe the working mechanism of GCL in SSNC, and find that the promotion brought by GCL is severely unevenly distributed: the improvement mainly comes from subgraphs with less annotated information, which is fundamentally different from contrastive learning in other fields. However, existing GCL methods generally ignore this uneven distribution of annotated information and apply GCL evenly to the whole graph. To remedy this issue and further improve GCL in SSNC, we propose the Topology InFormation gain-Aware Graph Contrastive Learning (TIFA-GCL) framework that considers the annotated information distribution across graph in GCL. Extensive experiments on six benchmark graph datasets, including the enormous OGB-Products graph, show that TIFA-GCL can bring a larger improvement than existing GCL methods in both transductive and inductive settings. Further experiments demonstrate the generalizability and interpretability of TIFA-GCL.

📄 PDF Abstract BibTeX arXiv:2012.07437

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning Graph Learning Node Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Rethinking Weak Supervision in Helping Contrastive Learning

2023-06-07 · Jingyi Cui, Weiran Huang, Yifei Wang, Yisen Wang

Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noi…

Contrastive Learning Denoising Weakly-supervised Learning

Revisiting Pretraining for Semi-Supervised Learning in the Low-Label Regime

2022-05-06 · Xun Xu, Jingyi Liao, Lile Cai, Manh Cuong Nguyen 외

Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labels could be incorrect, a.k.a. the confir…

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective

2023-02-03 · NeurIPS 2023 11 · Chenyu You, Weicheng Dai, Yifei Min, Fenglin Liu 외

For medical image segmentation, contrastive learning is the dominant practice to improve the quality of visual representations by contrasting semantically similar and dissimilar pairs of samples. This is enabled by the o…

Contrastive Learning Image Segmentation Medical Image Segmentation Segmentation+2

Using contrastive learning to improve the performance of steganalysis schemes

2021-03-01 · Yanzhen Ren, YiWen Liu, Lina Wang

To improve the detection accuracy and generalization of steganalysis, this paper proposes the Steganalysis Contrastive Framework (SCF) based on contrastive learning. The SCF improves the feature representation of stegana…

Contrastive Learning Steganalysis

Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation

2022-10-23 · Atsuyuki Miyai, Qing Yu, Daiki Ikami, Go Irie 외

Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated image is always treated as either positi…

Contrastive Learning Data Augmentation