arXiv cs.AI· Gwenol\'e Quellec·· 10 小时前AI 评分29
竞争性约束如何揭示表征学习的本质
What competing constraints reveal about representation learning
AI 导读
研究提出预测充分性、最小性、时间一致性、观测兼容性、无关变化不变性与结构约束六项互补属性,用于厘清表征应保留、丢弃和组织哪些信息。受控合成实验显示,看似有利的诊断指标与表征实际保留的信息存在偏差,且预测性能相当时潜坐标仍存在歧义。该分析为设计、比较和评估学习到的潜状态提供了依据,成果已被 Patterns(Cell Press)接收。
正文 · 原文
Abstract:Learning latent states from temporal, multimodal, and partially observed data requires decisions about what information representations should retain, discard, and organize. I argue that six complementary properties help clarify these decisions: predictive sufficiency, minimality, temporal coherence, observation compatibility, nuisance invariance, and structural constraints. Drawing on established approaches, I distinguish desired representation properties from the objectives used to encourage them and the diagnostics used to assess them, since neither a training objective nor an evaluation metric guarantees that a property has been achieved. Controlled synthetic experiments examine how training objectives influence predictive performance, nuisance decodability, and latent organization. The results reveal discrepancies between seemingly favorable diagnostics and the information retained in learned representations, as well as latent-coordinate ambiguities under equivalent predictive performance, illustrating how complementary evaluations can improve interpretation and guide design choices. Together, these analyses provide a basis for designing, comparing, and evaluating learned latent states.
| Comments: | Accepted for publication in Patterns (Cell Press). Code repository: this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.15995 [cs.LG] |
| (or arXiv:2605.15995v5 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15995 arXiv-issued DOI via DataCite |
Submission history
From: Gwenole Quellec [view email]
[v1]
Fri, 15 May 2026 14:25:40 UTC (250 KB)
[v2]
Thu, 23 Jul 2026 16:07:36 UTC (547 KB)
[v3]
Wed, 7 Oct 2026 11:34:25 UTC (552 KB)
[v4]
Mon, 16 Nov 2026 15:33:07 UTC (552 KB)
[v5]
Wed, 18 Nov 2026 13:46:20 UTC (969 KB)
来源:arXiv cs.AI · arxiv.org