From Overlooked to Explored: Recovering Item Relations via Mixture of Perspectives for Sequential Recommendation
Through empirical analysis, this work identifies a "similarity bias" in dot-product self-attention that systematically overlooks heterogeneous item relations carrying causal signal for target prediction, and proposes PRISM, a module that calibrates attention through K Perspective Lenses operating in two complementary views, an Affinity View and a Contrast View, consistently outperforming state-of-the-art baselines on seven real-world benchmarks.