AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Unsupervised Graph Embedding via Adaptive Graph Learning

Rui Zhang, Yunxing Zhang, Chengjun Lu, Xuelong Li

TPAMI 2022 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 45 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
Replace GCN autoencoder (GAE) with adaptive graph learning plus Laplacian term (BAGE)GAE · Cora clustering (0% missing edges)ACC (%): 59.53 -> 72.57Improved
Use BAGE instead of strongest baseline ARGEARGE · Cora clustering (50% missing edges)ACC (%): 55.21 -> 64.22Improved
Use VBAGE instead of ARVGEARVGE · Cora clustering (0% missing edges)ACC (%): 67.66 -> 73.11Improved
Use BAGE instead of ARGEARGE · Citeseer clustering (0% missing edges)ACC (%): 58.67 -> 64.64Improved
Use BAGE instead of ARGE at heavy edge lossARGE · Citeseer clustering (50% missing edges)ACC (%): 45.42 -> 39.91Hurt
Use BAGE instead of LGAE at heavy edge lossLGAE · Citeseer clustering (50% missing edges)ACC (%): 46.83 -> 39.91Hurt
Increase missing edge ratio from 0% to 50% for BAGE (ablation)BAGE · Cora clusteringACC (%): 72.57 -> 64.22Hurt
Increase missing edge ratio from 0% to 50% for GAE (ablation)GAE · Cora clusteringACC (%): 59.53 -> 48.77Hurt
Use adaptive adjacency instead of kNN-initialised graph (BAGE vs GAE)GAE · COIL node classificationF1 (%): 93.86 -> 97.50Improved
Use BAGE instead of GAE on ATTGAE · ATT node classificationF1 (%): 78.48 -> 86.59Improved
Use BAGE instead of GAE on PIEGAE · PIE node classificationF1 (%): 87.69 -> 95.29Improved
Use VBAGE instead of BAGE on IMMBAGE · IMM node classificationF1 (%): 36.71 -> 25.81Hurt

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