FAIRSHIFT: CONTROLLER-ONLY FAIRNESS ADAPTATION OF PRETRAINED GRAPH DIFFUSION MODELS

Fairness gaps in link prediction may reflect structural bias embedded in graph data rather than only bias in the downstream model. We therefore study fair topology generation as a data-level intervention. A pretrained graph generator should be reusable when fairness requirements change. We propose FairShift, a post-training controller that adjusts edge formation during reverse diffusion while keeping the denoiser frozen. A persistent score state supplies guidance for statistical parity (SP) or score-based equal opportunity (EO). FairShift-T calibrates a $T$-parameter logit-shift schedule from replayed trajectories, whereas FairShift-F uses a constant shift strength without controller optimization. We evaluate generated graphs through the utility and fairness of link predictors trained on them. Relative to the corresponding uncontrolled EDGE-cond backbones, selected retention-oriented FairShift-T configurations reduce SP by $47.1\%$, $45.7\%$, and $23.6\%$ on Cora, Citeseer, and Amazon Photo, respectively, with AUC decreases of $1.02$, $0.93$, and $0.53$ percentage points. The edge-logit interface also supports a joint feature–edge diffusion backbone and EO control. These results demonstrate reusable fairness adaptation across the evaluated backbones and objectives without fairness-specific denoiser retraining. Code and supplementary materials are available at https://anonymous.4open.science/r/FairShift-A6CB.