DeepAI AI Chat
Log In Sign Up

Contrastive Self-supervised Learning for Graph Classification

by   Jiaqi Zeng, et al.

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 prone to overfitting. To address this problem, we propose two approaches based on contrastive self-supervised learning (CSSL) to alleviate overfitting. In the first approach, we use CSSL to pretrain graph encoders on widely-available unlabeled graphs without relying on human-provided labels, then finetune the pretrained encoders on labeled graphs. In the second approach, we develop a regularizer based on CSSL, and solve the supervised classification task and the unsupervised CSSL task simultaneously. To perform CSSL on graphs, given a collection of original graphs, we perform data augmentation to create augmented graphs out of the original graphs. An augmented graph is created by consecutively applying a sequence of graph alteration operations. A contrastive loss is defined to learn graph encoders by judging whether two augmented graphs are from the same original graph. Experiments on various graph classification datasets demonstrate the effectiveness of our proposed methods.


Self-supervised Regularization for Text Classification

Text classification is a widely studied problem and has broad applicatio...

Latent Augmentation For Better Graph Self-Supervised Learning

Graph self-supervised learning has been vastly employed to learn represe...

Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory

Most NLP datasets are manually labeled, so suffer from inconsistent labe...

Group Contrastive Self-Supervised Learning on Graphs

We study self-supervised learning on graphs using contrastive methods. A...

Contrastive Graph Learning for Population-based fMRI Classification

Contrastive self-supervised learning has recently benefited fMRI classif...

Unsupervised Task Graph Generation from Instructional Video Transcripts

This work explores the problem of generating task graphs of real-world a...

Improving Domain-Invariance in Self-Supervised Learning via Batch Styles Standardization

The recent rise of Self-Supervised Learning (SSL) as one of the preferre...