arXiv：cs.LG· Peilun Li, Kaiyuan Tan, Daniel Moyer, Thomas Beckers·· 5 小时前AI 评分32
CIPHER：从部分观测中对比学习潜在 Port-Hamiltonian 动力学
Identify then Realize: Contrastive Learning of Latent Port-Hamiltonian Dynamics from Partial Observations
AI 导读
研究者提出 CIPHER，一个“先辨识、后实现”的两阶段框架，用于从部分高维观测中学习保守与耗散系统的潜在 Port-Hamiltonian 模型。第一阶段用对比教师联合学习编码器与神经 ODE 获得预测性状态表示，第二阶段由学生通过匹配编码后的观测未来学习可逆非线性坐标变换与 Port-Hamiltonian 动力学。
正文
Abstract:Identifying latent state representations and dynamics is essential when direct modeling in observation space is infeasible, particularly under partial and high-dimensional observations. In such settings, representation learning and physics-aware modeling are inherently coupled. We propose CIPHER, a two-stage identify-then-realize framework for learning latent port-Hamiltonian models of conservative and dissipative systems. First, a contrastive teacher jointly learns an encoder and a neural ODE to obtain predictive state representations from observation histories. Second, a student learns an invertible nonlinear coordinate transformation and port-Hamiltonian dynamics by matching encoded observed futures. We establish sufficient conditions for recovering the physical state up to a diffeomorphism and realizing its dynamics in port-Hamiltonian form. Across ten clean and noisy datasets, CIPHER is competitive with or outperforms state-of-the-art baselines by improving long-horizon forecast on complex systems. Further studies show robustness to over-specified latent dimensions and additional predictive gains from pH parameterization.
| Comments: | v2 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.16682 [cs.LG] |
| (or arXiv:2605.16682v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16682 arXiv-issued DOI via DataCite |
Submission history
From: Peilun Li [view email]
[v1]
Fri, 15 May 2026 22:39:24 UTC (4,062 KB)
[v2]
Thu, 1 Oct 2026 21:38:40 UTC (9,122 KB)
来源：arXiv：cs.LG · arxiv.org