AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs

Zehao Dong, Muhan Zhang, Fuhai Li, Yixin Chen

ICML 2022 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 3 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 PACE instead of DAGNNDAG encoding and performance prediction · NARMSE: 0.264 ± 0.004 -> 0.254 ± 0.002Improved
Use PACE instead of DAGNNDAG encoding and performance prediction · BNRMSE: 0.122 ± 0.004 -> 0.115 ± 0.004Improved
Use PACE instead of DAGNNDAG encoding for code token prediction · OGBG-CODE2test F1: 0.1751 ± 0.0049 -> 0.1779 ± 0.0021Improved
Add masked attention to dag2seq + Transformer (ablation)PACE · NARMSE: 0.255 -> 0.254Improved
Add masked attention to dag2seq + Transformer (ablation)PACE · BNRMSE: 0.119 -> 0.115Improved
Add masked attention to dag2seq + Transformer (ablation)PACE with NAS101 DNGO search · NAS101regret (%): 0.479 -> 0.391Improved
Add masked attention to dag2seq + Transformer (ablation)PACE with NAS301 DNGO search · NAS301accuracy (%): 94.501 -> 94.507Improved
Add dag2seq positional encoding and attention mask (ablation)PACE · NARMSE: 0.981 -> 0.254Improved
Add dag2seq positional encoding and attention mask (ablation)PACE · BNRMSE: 0.368 -> 0.115Improved
Add dag2seq positional encoding and attention mask (ablation)PACE with NAS101 DNGO search · NAS101regret (%): 0.600 -> 0.391Improved
Add dag2seq positional encoding and attention mask (ablation)PACE with NAS301 DNGO search · NAS301accuracy (%): 94.467 -> 94.507Improved
Use PACE rather than DAGNNDAG encoding on OGBG-CODE2 · OGBG-CODE2training time (min): 166.19 ± 3.52 -> 40.71 ± 0.19Improved

Later papers that compared with this method

1 later accepted paper reports PACE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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