AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Robust Graph Structure Learning via Multiple Statistical Tests

Yaohua Wang, Fangyi Zhang, Ming Lin, Senzhang Wang, Xiuyu Sun, Rong Jin

NeurIPS 2022 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 2 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 multiple-test AUC similarity instead of single-test similarity as k grows from 5 to 40Sim-M vs Sim-S on MS-Celeb Part1 · MS-Celeb Part1, k=5 to k=40AUC: 96.80 -> 97.59; 96.21 -> 97.72; 95.33 -> 97.21; 94.00 -> 95.66Improved
Use multiple-test similarity when the neighbourhood contains too much noiseSim-M on MS-Celeb Part1 · MS-Celeb Part1, k=80 to k=160AUC: 92.05 -> 91.32; 90.76 -> 86.58; 90.65 -> 83.90Hurt
Use multiple-test similarity rather than single-test similaritySim-M on MSMT17 · MSMT17, k=5 to k=20AUC: 89.23 -> 89.74; 89.33 -> 90.02; 87.78 -> 88.63Improved
Use multiple-test similarity rather than single-test similaritySim-M on VeRi-776 · VeRi-776, k=5 to k=40AUC: 90.96 -> 90.40; 89.34 -> 90.09; 85.86 -> 86.54; 83.05 -> 82.89Mixed
Add A_band attention to the GCNGCN · MS-Celeb Part1, MSMT17, VeRi-776mAP: 90.15 -> 95.97; 83.51 -> 86.04; 85.27 -> 87.59Improved
Use the proposed learned graph features with Infomap rather than original featuresInfomap clustering · MS-Celeb Part1Pairwise F-score: 93.91 -> 94.94Improved
Add Q-attention to self-attention in the combined A_band design (ablation)GCN w/ A_band on MS-Celeb Part1 · MS-Celeb Part1mAP: 88.10 -> 95.97Improved
Use A_X rather than A_self as the input to Q-attention (ablation)GCN attention architecture on MS-Celeb Part1 · MS-Celeb Part1mAP: 90.10 -> 92.26Improved
Add learnable W_qart query and key weights (ablation)A_band on MS-Celeb Part1 · MS-Celeb Part1mAP: 93.67 -> 95.97Improved
Use learned weighted addition rather than unweighted addition to fuse attention maps (ablation)A_band · MS-Celeb, MSMT17, VeRi-776mAP: 92.83 -> 95.97; 84.95 -> 86.04; 85.97 -> 87.59Improved
Use learned weighted addition rather than element-wise multiplication to fuse attention maps (ablation)A_band · MS-Celeb, MSMT17, VeRi-776mAP: 95.71 -> 95.97; 85.59 -> 86.04; 85.53 -> 87.59Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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