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

Signed graphs consist of edges and signs, which can be separated intostructural information and balance-related information, respectively. Existingsigned graph neural networks (SGNNs) typically rely on balance-relatedinformation to generate embeddings. Nevertheless, the emergence of recentadversarial attacks has had a detrimental impact on the balance-relatedinformation. Similar to how structure learning can restore unsigned graphs,balance learning can be applied to signed graphs by improving the balancedegree of the poisoned graph. However, this approach encounters the challenge"Irreversibility of Balance-related Information" - while the balance degreeimproves, the restored edges may not be the ones originally affected byattacks, resulting in poor defense effectiveness. To address this challenge, wepropose a robust SGNN framework called Balance Augmented-Signed GraphContrastive Learning (BA-SGCL), which combines Graph Contrastive Learningprinciples with balance augmentation techniques. Experimental resultsdemonstrate that BA-SGCL not only enhances robustness against existingadversarial attacks but also achieves superior performance on link signprediction task across various datasets.

Adversarially Robust Signed Graph Contrastive Learning from Balance Augmentation