AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Evolutionarily Learning Multi-Aspect Interactions and Influences from Network Structure and Node Content

Songlei Jian, Liang Hu, Longbing Cao, Kai Lu, Hang Gao

AAAI 2019 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 5 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
add multi-aspect influence propagation system to MAI-LS (MAI-LS -> MAI-ECS) (ablation)MAI-LS · Aminer citation node classification, 80%accuracy: 0.857 -> 0.887Improved
add multi-aspect influence propagation system to MAI-LS (ablation)MAI-LS · Aminer citation node classification, 80%F1-score: 0.802 -> 0.832Improved
add multi-aspect influence propagation system to MAI-LS (ablation)MAI-LS · Aminer citation node classification, 20%accuracy: 0.845 -> 0.873Improved
add multi-aspect influence propagation system to MAI-LS (ablation)MAI-LS · Aminer citation node classification, 20%F1-score: 0.783 -> 0.815Improved
add influence propagation to MAI-LS (ablation)MAI-LS · Aminer Coauthor link predictionnDCG@1: 0.956 -> 0.965Improved
add influence propagation to MAI-LS (ablation)MAI-LS · Aminer Citation link predictionnDCG@1: 0.805 -> 0.820Improved
add influence propagation to MAI-LS (ablation)MAI-LS · Aminer Citation link predictionnDCG@10: 0.889 -> 0.898Improved
use network structure (Node2vec) instead of node content only (Doc2vec)embedding input · Aminer citation node classification, 80%accuracy: 0.658 -> 0.804Improved
use network structure (Node2vec) instead of node content only (Doc2vec)embedding input · Aminer Citation link predictionnDCG@1: 0.385 -> 0.716Improved
concatenate Node2vec and Doc2vec (NV+DV) vs Node2vec aloneembedding input · Aminer citation node classification, 80%accuracy: 0.804 -> 0.838Improved
use NV+DV concatenation instead of CANE with separate objectivesbaseline choice · Aminer citation node classification, 80%accuracy: 0.820 -> 0.838Improved
use NV+DV concatenation instead of TriDNRbaseline choice · Aminer citation node classification, 80%accuracy: 0.817 -> 0.838Improved

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