AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Premise Selection for Theorem Proving by Deep Graph Embedding

Mingzhe Wang, Yihe Tang, Jian Wang, Jia Deng

NeurIPS 2017 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 75 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use order-preserving graph updates instead of FormulaNet-basic updatesFormulaNet · HolStep test, conditional premise selectionaccuracy: 89.1 -> 90.3Improved
Use graph-based formula embeddings rather than the strongest sequence baselineHolStep · HolStep test, conditional premise selectionaccuracy: 83 -> 90.3Improved
Use graph structure rather than an unstructured token bag (ablation)FormulaNet-basic · HolStep validation, conditional premise selectionaccuracy: 81.5 -> 89.9Improved
Use a parse tree instead of the variable-linked graph, with variables renamed (ablation)FormulaNet-basic · Original Validationaccuracy: 89.9 -> 84.7Hurt
Use a parse tree instead of the variable-linked graph, with variables renamed (ablation)FormulaNet-basic · Renamed Validationaccuracy: 89.9 -> 84.7Hurt
Retain original variable names instead of making the graph invariant to renaming (ablation)FormulaNet-basic · Renamed Validationaccuracy: 89.9 -> 83.5Hurt
Retain original variable names instead of making the tree invariant to renaming (ablation)FormulaNet-basic · Renamed Validationaccuracy: 89.9 -> 82.3Hurt
Increase FormulaNet-basic update depth from 0 to 3 steps (ablation)FormulaNet-basic · HolStep validation, conditional premise selectionaccuracy: 81.5 -> 89.9Improved
Increase FormulaNet update depth from 0 to 3 steps (ablation)FormulaNet · HolStep validation, conditional premise selectionaccuracy: 81.5 -> 91.1Improved
Increase FormulaNet update depth from 3 to 4 steps (ablation)FormulaNet · HolStep validation, conditional premise selectionaccuracy: 91.1 -> 90.8Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy