AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions

Michael Scholkemper, Michael T Schaub

NeurIPS 2023 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 1 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 the EV-based graph embedding instead of Graph2VecFew-shot graph classification · AIDSaccuracy: 79.9± 4.4 -> 95.0 ± 5.2Improved
Use the EV-based graph embedding instead of Graph2VecFew-shot graph classification · ENZYMESaccuracy: 20.3± 1.5 -> 21.3± 1.7Improved
Use the EV-based graph embedding instead of Graph2VecFew-shot graph classification · PROTEINSaccuracy: 60.3± 3.5 -> 66.5± 6.4Improved
Use the EV-based graph embedding instead of Graph2VecFew-shot graph classification · NCI1accuracy: 53.9± 1.5 -> 58.5± 4.0Improved
Use the EV-based graph embedding instead of Graph2VecFew-shot graph classification · MUTAGaccuracy: 66.9± 5.6 -> 81.5± 7.7Improved
Train GIN on 90% of the dataset instead of using the EV embedding with 10 training examplesGraph classification · AIDSaccuracy: 95.0 ± 5.2 -> 97.8 ± 1.4Improved
Train GIN on 90% of the dataset instead of using the EV embedding with 10 training examplesGraph classification · ENZYMESaccuracy: 21.3± 1.7 -> 60.3 ± 0.7Improved
Train GIN on 90% of the dataset instead of using the EV embedding with 10 training examplesGraph classification · PROTEINSaccuracy: 66.5± 6.4 -> 75.4 ± 1.3Improved
Train GIN on 90% of the dataset instead of using the EV embedding with 10 training examplesGraph classification · NCI1accuracy: 58.5± 4.0 -> 82.0 ± 0.3Improved
Train GIN on 90% of the dataset instead of using the EV embedding with 10 training examplesGraph classification · MUTAGaccuracy: 81.5± 7.7 -> 94.3 ± 0.5Improved
Use fuzzy c-means rather than average linkage in approximate WLApproximate WL on RIP planted-role recovery · RIP planted-role recoveryrecovery accuracyImproved
Use EV-based clustering rather than the other tested methodsLong-term cost minimization · RIP planted-role recoverylong-term costImproved

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