A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples.

Dec 18, 2023 · This paper proposes a novel framework called Debiased Graph Contrastive Learning Based on Positive and Unlabeled Learning (DGCL-PU).

Oct 1, 2023 · We propose Two-Level Debiased Contrastive Graph Learning (TDCGL) model. Specifically, we design the Two-Level Debiased Contrastive Learning (TDCL) and deploy ...

We propose a graph debiased contrastive learning framework, which can jointly perform representation learning and clustering.

By contrasting positive-negative counterparts, graph contrastive learning has become a prominent technique for unsupervised graph representation learning.

Given an unlabeled graph G, our goal is to develop a debiased graph contrastive learning frame- work that incorporates the knowledge of model discrepancy ...

This is the pytorch implementation of Graph Debiased Contrastive Learning (GDCL) model that is published in IJCAI 2021.

Aug 19, 2024 · We use it as a guide to develop a novel Debiased Contrastive Learning framework for Mitigating Dual Biases, called DCLMDB.

However, we find that the training process of contrastive learning is affected by the popularity bias due to the longtail distribution of interaction data, ...

Mar 8, 2024 · This paper aims to tackle the problem of sampling bias in graph contrastive learning, which stems from the arbitrary selection process of ...