AI Paper Atlas

Research map / Graph learning / GNN architectures

Leap of FAITH from GNN-to-MLP: Fairness Aware Inference via DisTillation of GrapH Knowledge

Vipul Kumar Singh, Jyotismita Barman, Sandeep Kumar, Tapan K. Gandhi, , Jayadeva

AAAI 2026 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 0 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 GLNN-style soft-label distillation with FAITH (energy alignment + l2,1 fairness)GNN-to-MLP distillation · Cora (transductive)individual unfairness IF x10^3: 71.13 -> 12.06Improved
use FAITH instead of TINED global energy alignmentMLP student, SAGE teacher · Pubmed (transductive)accuracy (%): 75.51 -> 81.53Improved
use FAITH instead of KRDMLP student, Co-author CS · CS (inductive)accuracy (%): KRD 92.50 vs FAITH 92.74Mixed
use FAITH instead of KRD in transductive CSMLP student · CS (transductive)accuracy (%): 93.99 -> 93.37Hurt
add neighborhood-guided Dirichlet energy distribution (DED) block (ablation)FAITH · transductive node classificationaccuracy/fairnessImproved
add oracle similarity alignment (OSA, l2,1) block (ablation)FAITH · transductive node classificationaccuracy/fairnessImproved
add counterfactual invariance group-fairness term (FAITH*) (ablation)FAITH · Credit and IncomeBPC (group+individual fairness balance)Improved
FAITH without group fairness termFAITH · Credit and Incomegroup fairnessHurt
use l2,1 norm instead of l2 norm for similarity regularizer (ablation)FAITH · node classification (Appendix F)sparsity and utility-fairness trade-offImproved
change teacher GNN to GCN, GAT or APPNP (ablation)FAITH · Cora, Pubmed, A-Photoaccuracy and IFNo clear effect
vary hyperparameters alpha, beta, gamma (ablation)FAITH · Coraaccuracy and IFNo clear effect

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