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

Using reinforcement learning for automated theorem proving has recentlyreceived much attention. Current approaches use representations of logicalstatements that often rely on the names used in these statements and, as aresult, the models are generally not transferable from one domain to another.The size of these representations and whether to include the whole theory orpart of it are other important decisions that affect the performance of theseapproaches as well as their runtime efficiency. In this paper, we presentNIAGRA; an ensemble Name InvAriant Graph RepresentAtion. NIAGRA addresses thisproblem by using 1) improved Graph Neural Networks for learning name-invariantformula representations that is tailored for their unique characteristics and2) an efficient ensemble approach for automated theorem proving. Ourexperimental evaluation shows state-of-the-art performance on multiple datasetsfrom different domains with improvements up to 10% compared to the bestlearning-based approaches. Furthermore, transfer learning experiments show thatour approach significantly outperforms other learning-based approaches by up to28%.

An Ensemble Approach for Automated Theorem Proving Based on Efficient Name Invariant Graph Neural Representations