Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity
This work addresses the limitation in structured prediction where supervision typically provides only a single output instance, failing to capture the true multimodal nature of the underlying distribution. To overcome this, the authors propose the Contextual Plackett-Luce (CPL) model, which incorporates unary and pairwise interaction terms through an Ising-style parameterization. CPL decouples parallel scoring from lightweight autoregressive selection, thereby enhancing multimodal expressiveness while maintaining computational efficiency. Empirical results demonstrate that the method significantly outperforms strong parallel baselines on multimodal trajectory prediction and representative subset selection tasks, yielding outputs with improved structural consistency and greater robustness to ambiguous supervision.