LocalGCL: Local-aware Contrastive Learning for Graphs

arXiv:2402.17345v1 Announce Type: new
Abstract: Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually prompts the growth of self-supervised learning (SSL) techniques. As a dominant approach of SSL, Contrastive learning (CL) learns discriminative representations by differentiating between positive and negative samples. However, when applied to graph data, it overemphasizes global patterns while neglecting local structures. To tackle the above issue, we …

abstract arxiv cs.ai cs.lg embeddings graph graph representation graphs growth labels low process progress prompts representation representation learning self-supervised learning ssl supervised learning type