English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph Contrastive Learning (GCL) has shown promising performance in graphrepresentation learning (GRL) without the supervision of manual annotations.GCL can generate graph-level embeddings by maximizing the Mutual Information(MI) between different augmented views of the same graph (positive pairs).However, the GCL is limited by dimensional collapse, i.e., embedding vectorsonly occupy a low-dimensional subspace. In this paper, we show that thesmoothing effect of the graph pooling and the implicit regularization of thegraph convolution are two causes of the dimensional collapse in GCL. Tomitigate the above issue, we propose a non-maximum removal graph contrastivelearning approach (nmrGCL), which removes "prominent'' dimensions (i.e.,contribute most in similarity measurement) for positive pair in the pre-texttask. Comprehensive experiments on various benchmark datasets are conducted todemonstrate the effectiveness of nmrGCL, and the results show that our modeloutperforms the state-of-the-art methods. Source code will be made publiclyavailable.

On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach