AI Paper Atlas

Research map / Graph learning / GNN architectures

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

David Bieber, Charles A. Sutton, Hugo Larochelle, Daniel Tarlow

NeurIPS 2020 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 9 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 IPA-GNN instead of NoExecute, retaining instruction-pointer attention and control flow while replacing execution components (ablation)IPA-GNN · D_test full program executionaccuracy (%): 50.7 -> 62.1Improved
use IPA-GNN instead of NoControl, retaining interpreter-like execution while replacing control-flow components (ablation)IPA-GNN · D_test full program executionaccuracy (%): 28.1 -> 62.1Improved
add IPA-GNN execution and control-flow components rather than use GGNNGGNN · D_test full program executionaccuracy (%): 16.0 -> 62.1Improved
use IPA-GNN instead of Line-by-Line RNNprogram execution models · D_test full program executionaccuracy (%): 32.0 -> 62.1Improved
use bounded IPA-GNN execution rather than the trace-oracle RNNprogram execution models · D_test full program executionaccuracy (%): 66.4 -> 62.1Hurt
use IPA-GNN instead of NoExecute, retaining instruction-pointer attention and control flow while replacing execution components (ablation)IPA-GNN · D_test partial program executionaccuracy (%): 20.7 -> 29.1Improved
use IPA-GNN instead of NoControl, retaining interpreter-like execution while replacing control-flow components (ablation)IPA-GNN · D_test partial program executionaccuracy (%): 8.1 -> 29.1Improved
add IPA-GNN execution and control-flow components rather than use GGNNGGNN · D_test partial program executionaccuracy (%): 5.7 -> 29.1Improved
use IPA-GNN instead of Line-by-Line RNNprogram execution models · D_test partial program executionaccuracy (%): 11.5 -> 29.1Improved

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