BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation

ArXi:2606.03091v1 Announce Type: cross Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution induces severe signal heterogeneity: dense head sequences trigger the solidification of teacher preference, biasing extraction toward local patterns, while sparse tail sequences yield flat, noisy predictions.