AI Paper Atlas

Research map / Graph learning / GNN architectures

Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

Shaohua Fan, Xiao Wang, Yanhu Mo, Chuan Shi, Jian Tang

NeurIPS 2022 · Graph learning › GNN architectures · approach: Graph structure learning · 37 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
Apply DisC to GCN instead of vanilla GCNGCN · CMNIST-75sp unbiased testing, bias degrees 0.8/0.9/0.95accuracy: 50.43_{\pm 4.13} -> 82.60_{\pm 0.93}; 28.97_{\pm 4.4} -> 78.14_{\pm 2.14}; 13.50_{\pm 1.38} -> 63.47_{\pm 5.65}Improved
Apply DisC to GIN instead of vanilla GINGIN · CMNIST-75sp unbiased testing, bias degrees 0.8/0.9/0.95accuracy: 57.75_{\pm 0.78} -> 82.10_{\pm 1.50}; 36.78_{\pm 5.55} -> 74.90_{\pm 1.81}; 16.04_{\pm 1.14} -> 58.58_{\pm 4.24}Improved
Apply DisC to GCNII instead of vanilla GCNIIGCNII · CMNIST-75sp unbiased testing, bias degrees 0.8/0.9/0.95accuracy: 69.70_{\pm 1.73} -> 79.50_{\pm 2.48}; 57.68_{\pm 1.68} -> 76.00_{\pm 1.90}; 41.00_{\pm 3.75} -> 60.54_{\pm 5.33}Improved
Apply DisC to GCN instead of vanilla GCNGCN · CFashion-75sp unbiased testingaccuracy: 63.60_{\pm 0.53} -> 66.85_{\pm 1.11}; 57.22_{\pm 0.93} -> 65.33_{\pm 4.70}; 47.69_{\pm 0.42} -> 63.93_{\pm 1.50}Improved
Apply DisC to GIN instead of vanilla GINGIN · CFashion-75sp unbiased testingaccuracy: 64.25_{\pm 0.46} -> 67.10_{\pm 1.07}; 58.03_{\pm 0.40} -> 59.90_{\pm 1.31}; 49.74_{\pm 0.60} -> 55.80_{\pm 0.36}Improved
Apply DisC to GCNII instead of vanilla GCNIIGCNII · CFashion-75sp unbiased testingaccuracy: 66.68_{\pm 0.59} -> 66.47_{\pm 1.77}; 60.58_{\pm 0.28} -> 65.48_{\pm 0.70}; 53.18_{\pm 0.08} -> 61.75_{\pm 0.27}Mixed
Apply DisC to GCN instead of vanilla GCNGCN · CKuzushiji-75sp unbiased testingaccuracy: 38.45_{\pm 1.1} -> 55.53_{\pm 2.29}; 28.35_{\pm 0.79} -> 48.13_{\pm 2.59}; 20.70_{\pm 0.88} -> 36.63_{\pm 1.73}Improved
Apply DisC to GIN instead of vanilla GINGIN · CKuzushiji-75sp unbiased testingaccuracy: 41.83_{\pm 0.78} -> 55.18_{\pm 1.00}; 30.09_{\pm 0.87} -> 41.75_{\pm 0.81}; 21.18_{\pm 1.63} -> 30.25_{\pm 1.63}Improved
Apply DisC to GCNII instead of vanilla GCNIIGCNII · CKuzushiji-75sp unbiased testingaccuracy: 48.53_{\pm 0.25} -> 54.90_{\pm 1.30}; 36.23_{\pm 0.20} -> 44.73_{\pm 1.55}; 25.60_{\pm 0.76} -> 36.95_{\pm 0.70}Improved
Add counterfactual sample generation to DisC without generation (ablation)DisC · Three datasets, averaged over bias degreesaccuracyImproved
Remove the learned edge mask module, using LDD-style disentanglement (ablation)DisC · Three datasets, most casesaccuracyHurt
Use near-CE bias loss with q=0.1 rather than the tested larger q values (ablation)DisC_GCN · CMNIST-75sp hyperparameter experimentaccuracyHurt

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