AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Cost-aware Graph Generation: A Deep Bayesian Optimization Approach

Jiaxu Cui, Bo Yang, Bingyi Sun, Jiming Liu

AAAI 2021 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 2 citations (OpenAlex)

Read the paper

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 CAGG instead of DGBOMolecular optimization · QM9, logP−SA# evaluations to find optimum: 189 -> 128Improved
Use CAGG instead of DGBOMolecular optimization · QM9, 5×QED−SA# evaluations to find optimum: 448 -> 144Improved
Use CAGG instead of DGBOMolecular optimization · QM9, logP−SAtotal cost (hours): 189.3 -> 129.2Improved
Use CAGG instead of DGBOMolecular optimization · QM9, 5×QED−SAtotal cost (hours): 449.0 -> 145.3Improved
Use CAGG with a 50.3-hour budget instead of REA with a 205-hour budgetCell-based NAS · CIFAR100classification accuracy (%): 73.09±0.25 -> 72.87±0.27Hurt
Use CAGG with a 50.3-hour budget instead of REA with a 205-hour budgetCell-based NAS · ImageNet16-120classification accuracy (%): 46.12±0.67 -> 46.13±0.46No clear effect
Increase CAGG budget from 50.3 to 140.9 hoursCell-based NAS · CIFAR100classification accuracy (%): 72.87±0.27 -> 73.25±0.42Improved
Increase CAGG budget from 50.3 to 140.9 hoursCell-based NAS · ImageNet16-120classification accuracy (%): 46.13±0.46 -> 46.34±0.27Improved
Use CAGG instead of NASGBOMulti-branch NAS · Indoormean squared error: 0.090±0.012 -> 0.063±0.001Improved
Use CAGG instead of NASGBOMulti-branch NAS · Slicemean squared error: 0.560±0.046 -> 0.433±0.010Improved
Use CAGG with a 4-hour budget instead of the 12-hour baselinesMulti-branch NAS · Indoormean squared error: best baseline 0.090±0.012; CAGG 0.072±0.003Improved
Use CAGG with an 8-hour budget instead of the 12-hour baselinesMulti-branch NAS · Slicemean squared error: 0.615±0.044 -> 0.625±0.001No clear effect

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