Label Contrastive Coding based Graph Neural Network for Graph Classification
Graph classification is a critical research problem in many applications from different domains. In order to learn a graph classification model, the most widely used supervision component is an output layer together with classification loss (e.g.,cross-entropy loss together with softmax or margin loss). In fact, the discriminative information among instances are more fine-grained, which can benefit graph classification tasks. In this paper, we propose the novel Label Contrastive Coding based Graph Neural Network (LCGNN) to utilize label information more effectively and comprehensively. LCGNN still uses the classification loss to ensure the discriminability of classes. Meanwhile, LCGNN leverages the proposed Label Contrastive Loss derived from self-supervised learning to encourage instance-level intra-class compactness and inter-class separability. To power the contrastive learning, LCGNN introduces a dynamic label memory bank and a momentum updated encoder. Our extensive evaluations with eight benchmark graph datasets demonstrate that LCGNN can outperform state-of-the-art graph classification models. Experimental results also verify that LCGNN can achieve competitive performance with less training data because LCGNN exploits label information comprehensively.
Code (1)
Tasks
ClassificationContrastive LearningGeneral ClassificationGraph ClassificationGraph Neural NetworkSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Supervised Graph Contrastive Learning for Few-shot Node Classification
Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis. But given the high cost of graph annotation or labeling, we face a severe gra…
ClassificationContrastive LearningData AugmentationFew-Shot Learning+3Graph Contrastive Learning for Anomaly Detection
Graph-based anomaly detection has been widely used for detecting malicious activities in real-world applications. Existing attempts to address this problem have thus far focused on structural feature engineering or learn…
Anomaly DetectionBinary ClassificationContrastive LearningFeature Engineering+1Contrastive Self-supervised Learning for Graph Classification
Graph classification is a widely studied problem and has broad applications. In many real-world problems, the number of labeled graphs available for training classification models is limited, which renders these models p…
ClassificationData AugmentationGeneral ClassificationGraph Classification+1Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training
Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning wit…
Contrastive LearningGraph LearningMeta-LearningNode ClassificationSupervised Contrastive Learning with Structure Inference for Graph Classification
Advanced graph neural networks have shown great potentials in graph classification tasks recently. Different from node classification where node embeddings aggregated from local neighbors can be directly used to learn no…
ClassificationContrastive LearningGraph ClassificationGraph Neural Network+1