发表机构
Politecnico di Milano（米兰理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对开放世界下演化标签空间的持续意图发现，提出不确定性感知概率框架，结合多信号决策与密度聚类实现受控标签扩展，实验显示高精确率与低遗忘。
AI 中文摘要
现实世界中的智能系统越来越多地在开放世界条件下运行，其中用户意图并非固定或先验地完全已知，并且可能随着新交互模式的出现而演化。本文提出了一种统一的、不确定性感知的概率框架，用于在演化标签空间下进行持续的新的意图发现。每个话语通过自适应β-VAE编码为潜在均值，用于分类和密度建模，以及作为全局可靠性信号的后验不确定性估计。分类器置信度、后验不确定性和DP-GMM似然通过多信号决策机制相结合，以区分已知意图与潜在的新样本。候选新实例通过基于密度的发现模块进行聚类，并且只有可靠的聚类被提升为新标签，从而实现受控的标签空间扩展。重放和弹性权重巩固缓解了灾难性遗忘并保留了先前获得的知识。本文将持续意图发现形式化为一个结构化的多阶段开放世界问题，在稳定性-可塑性约束下引入自适应标签空间扩展，并使用后验不确定性来调节可信样本选择、伪标签、新类别接纳和重放。实验表明，该方法具有较高的新类别精确率、跨连续阶段的稳定适应性以及有限的遗忘。接近零的NMI和ARI表明对完整细粒度意图分类体系的恢复有限，这与框架的保守提升策略一致。然而，定性分析揭示了密集且局部连贯的语义聚类，表明可以在不完全恢复底层分类体系的情况下发现可靠的新结构。
英文摘要
Real-world intelligent systems increasingly operate under open-world conditions, where user intents are not fixed or exhaustively known a priori and may evolve as new interaction patterns emerge. This paper proposes a unified uncertainty-aware probabilistic framework for continual new intent discovery under an evolving label space. Each utterance is encoded through an adaptive $β$-VAE into a latent mean, used for classification and density modelling and a posterior uncertainty estimate acting as a global reliability signal. Classifier confidence, posterior uncertainty and DP-GMM likelihood are combined through a multi-signal decision mechanism to distinguish known intents from potentially novel samples. Candidate novel instances are clustered through a density-based discovery module and only reliable clusters are promoted to new labels, enabling controlled label-space expansion. Replay and Elastic Weight Consolidation mitigate catastrophic forgetting and preserve previously acquired knowledge. The paper formalises continual intent discovery as a structured multi-phase open-world problem, introduces adaptive label-space expansion under stability--plasticity constraints and uses posterior uncertainty to regulate trusted-sample selection, pseudo-labelling, novelty admission and replay. Experiments show high novelty precision, stable adaptation across sequential phases and limited forgetting. Near-zero NMI and ARI indicate limited reconstruction of the complete fine-grained intent taxonomy, consistent with the framework's conservative promotion strategy. Qualitative analyses nevertheless reveal dense and locally coherent semantic clusters, showing that reliable novel structures can be discovered without exhaustive recovery of the underlying taxonomy.
