Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity

2026-05-09

AI Summary

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.

Abstract

Selecting a coherent sequence or subset of elements is a fundamental problem in structured prediction, arising in tasks such as detection, trajectory forecasting, and representative subset selection. In many such settings, the target is inherently ambiguous: each input admits multiple valid outputs, while supervision provides only a single sampled instance. This induces a mismatch between the underlying multi-modal target distribution and the observed training signal. We propose Contextual Plackett-Luce (CPL), a structured probabilistic model for sequence selection that extends the classical Plackett-Luce model to a context-dependent setting following an Ising-style parameterization with unary and pairwise interaction terms. CPL can be viewed as a hybrid between fully autoregressive prediction and parallel sequence selection: autoregressive models effectively capture uncertainty but are computationally expensive on modern parallel hardware such as GPUs, while parallel methods are efficient but struggle to represent multi-modal dependencies. CPL combines the strengths of both by constructing the parameters of a probabilistic selection model in a fully parallel manner, followed by a lightweight autoregressive selection process in which each step applies incremental updates to contextual logits. This decoupling of parallel scoring and sequential selection enables efficient computation without sacrificing expressivity. We evaluate CPL on two structured selection tasks: multi-modal path prediction and representative subset selection. CPL achieves improved structural consistency and robustness under ambiguous supervision compared to strong parallel baselines.

Problem

• structured prediction
• ambiguous supervision
• multi-modal output
• sequence selection
• probabilistic modeling

Innovation

• Contextual Plackett-Luce
• structured prediction
• multi-modal ambiguity
• parallel-autoregressive hybrid
• probabilistic sequence selection