arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.15995cs.LGcs.AI

受限潜在状态建模:在竞争约束下表示学习的统一视角

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

  • LaTIM UMR 1101

机构由 AI 辅助整理,请以论文原文为准。

Gwenolé Quellec

AI总结:

本文提出受限潜在状态建模(CLSM),统一了表示学习中在竞争约束下的核心原则与方法,揭示了潜在状态的内在耦合关系与根本权衡。

AI中文摘要:

从复杂数据中学习潜在表示是现代机器学习的核心,涵盖时间、多模态和部分观测系统。在这些设置中,表示应被视为捕捉系统动态的潜在状态,而非仅仅是观测的压缩总结。然而,当前方法仍碎片化,依赖于对这些状态应代表什么的不同且往往隐含的假设。我们主张这种碎片化反映了更根本的限制:潜在表示通常从欠约束的目标学习,未能指定有意义的潜在状态应满足的属性。因此,多个表示可以满足相同的目标,导致结构和解释的模糊性。尽管许多底层原则已被单独探索,但它们的相互作用尚未被显式形式化。在本文中,我们提出受限潜在状态建模(CLSM)作为统一的视角。我们识别了一组核心属性——预测充分性、最小性、时间一致性、观测兼容性、对干扰因素的不变性以及结构约束——并展示它们通过根本的权衡相互耦合。通过这一视角重新审视主要建模家族,我们显示现有方法可以被解释为强制不同的约束子集,从而占据共同设计空间的不同区域。这一视角将持续挑战如可识别性不足重新解释为欠约束形式的后果,而非孤立的技术限制。更广泛地说,CLSM提供了一个原则性的框架,以使设计选择显式化,分析权衡,并指导开发更具可解释性、稳健性和任务对齐的潜在状态模型。

英文摘要:

Learning latent representations from temporal, multimodal, and partially observed data requires specifying what information a latent state should retain, discard, and organize. Existing approaches encode these requirements through heterogeneous objectives, making methods difficult to compare and learned representations difficult to interpret. We propose Constrained Latent State Modeling (CLSM), a conceptual framework that characterizes latent states through six complementary properties: predictive sufficiency, minimality, temporal coherence, observation compatibility, invariance to nuisance factors, and structural constraints. CLSM separates these properties from the surrogate objectives used to induce them and from the diagnostics used to evaluate them, and clarifies how combinations of constraints can improve identifiability by restricting the space of admissible representations. We reinterpret major representation-learning families through this common design space and illustrate the framework with a controlled synthetic benchmark. The experiments show how objectives produce distinct latent organizations and empirical trade-offs depending on the prediction target, surrogate formulation, parameterization, and optimization. Companion repository containing the reference implementation, reproducible experiments, documentation, and model cards: https://github.com/gwenole-quellec/clsm

↑