提出通过检测潜在变量中的突变点实现无监督解耦。
Operationalizing Quantized Disentanglement
- 用轴对齐突变点（悬崖）作为解耦信号，引导模型学习。
- 在所有基准测试中超越基线，证明方法有效。
- 适合研究无监督表征学习与可解释性建模的学者。
近期理论工作证明了在任意微分同胚下，量化因子具有无监督可识别性。该理论假设量化阈值对应于潜在因子概率密度的轴对齐不连续性。通过约束学习映射的密度具有轴对齐不连续性，可恢复因子的量化。然而，将这一高层原则转化为有效的实用准则仍具挑战，尤其是在非线性映射下。本文提出一种基于鼓励轴对齐不连续性的无监督解耦准则。不连续性表现为因子估计密度的急剧变化，我们称之为‘悬崖’。根据理论定义的独立不连续性，我们鼓励某一因子的悬崖位置与其他因子取值无关。实验表明，所提方法Cliff在所有解耦基准上均优于基线，验证了其在无监督解耦中的有效性。
原文摘要 · Abstract (English)
Recent theoretical work established the unsupervised identifiability of quantized factors under any diffeomorphism. The theory assumes that quantization thresholds correspond to axis-aligned discontinuities in the probability density of the latent factors. By constraining a learned map to have a density with axis-aligned discontinuities, we can recover the quantization of the factors. However, translating this high-level principle into an effective practical criterion remains challenging, especially under nonlinear maps. Here, we develop a criterion for unsupervised disentanglement by encouraging axis-aligned discontinuities. Discontinuities manifest as sharp changes in the estimated density of factors and form what we call cliffs. Following the definition of independent discontinuities from the theory, we encourage the location of the cliffs along a factor to be independent of the values of the other factors. We show that our method, Cliff, outperforms the baselines on all disentanglement benchmarks, demonstrating its effectiveness in unsupervised disentanglement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。