AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

GraphOpt: Learning Optimization Models of Graph Formation

Rakshit Trivedi, Jiachen Yang, Hongyuan Zha

ICML 2020 · Graph learning › Graph algorithms and clustering · approach: Continuous DAG structure learning · 10 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 GraphOpt-Embed rather than SEALCora-ML link prediction · Cora-MLAUC: 97.21 -> 96.21Hurt
Use GraphOpt-Embed rather than SEALPolitical Blogs link prediction · Political BlogsAUC: 95.32 -> 95.50Improved
Use GraphOpt-Embed rather than SEALE. Coli link prediction · E. ColiAUC: 97.12 -> 97.20Improved
Use GraphOpt-Embed rather than the strongest baselineWN18RR link prediction · WN18RRMRR: 47.2 -> 47.3Improved
Transfer the learned Cora-ML reward and train a new policy, rather than directly deploy the Cora-ML policyCiteSeer graph construction · CiteSeerTriangle Count: 2234 ± 58.96 -> 2847.66 ± 57.13Improved
Transfer the learned Cora-ML reward and train a new policy, rather than directly deploy the Cora-ML policyCiteSeer graph construction · CiteSeerClustering Coeff.: 0.084 ± 0.004 -> 0.098 ± 0.0010Improved
Transfer the learned Cora-ML reward and train a new policy, rather than directly deploy the Cora-ML policyCiteSeer graph construction · CiteSeerMax Degree: 70.66 ± 2.081 -> 80.66 ± 1.527Improved
Learn and optimize a latent reward instead of directly transferring the trained policyCiteSeer graph construction · CiteSeerTriangle Count: 2234 ± 58.96 -> 2847.66 ± 57.13Improved
Use GraphOpt instead of NetGAN for graph synthesisBarabasi Albert graph construction · Barabasi AlbertTriangle Count deviation (%): 31.68 ± 6.28 -> 6.28 ± 4.05Improved
Use GraphOpt instead of NetGAN for graph synthesisPolitical Blogs graph construction · Political BlogsClustering Coeff. deviation (%): 37.55 ± 7.2 -> 20.34 ± 9.1Improved
Use a learned embedding for prediction rather than the GraphOpt construction policyCora-ML link prediction · Cora-MLAUC: 93.50 -> 96.21Improved
Use a learned embedding for prediction rather than the GraphOpt construction policyPolitical Blogs link prediction · Political BlogsAUC: 92.21 -> 95.50Improved

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