通过多阶段建模改进解耦表示学习器的重构效果
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
AI总结：
针对现有解耦表示学习中解耦效果与重构质量的权衡问题，提出多阶段建模方法，先学习解耦因子再用生成模型补充相关潜在变量细节，在多基准上实现同等解耦性能下更高重构质量，还可用于合成表格数据生成。
摘要：
当前基于自编码器的解耦表示学习方法通过对（聚合）后验分布施加惩罚以鼓励潜在因子的统计独立性，从而实现解耦。该方法会在解耦表示学习与重构质量之间产生权衡，因为模型没有足够的容量去学习能够捕捉大多数图像数据中细节信息的相关潜在变量。为克服这一权衡问题，我们提出了一种新颖的多阶段建模方法：首先使用基于惩罚的解耦表示学习方法学习解耦因子；随后，用另一个深度生成模型改善低质量的重构结果，该模型被训练用于建模缺失的相关潜在变量，在保留已学习解耦因子条件的同时补充细节信息。综上，我们的多阶段建模方法构建了一个统一连贯的概率模型，该模型在理论上由D-分离原理支撑，可通过多种模型类别实现，包括变分自编码器（VAE）等基于似然的模型、生成对抗网络（GAN）等隐式模型，以及归一化流或高斯混合等易处理模型。我们在多个标准基准上验证了，在解耦性能相当的情况下，我们的多阶段模型比现有最优方法具有更高的重构质量。此外，我们将多阶段模型应用于生成合成表格数据集，在多种指标上均表现出优于基准模型的性能。可解释性分析进一步表明，多阶段模型能够有效发现不同且有意义的变异特征，据此可恢复原始分布。
英文摘要：
Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between disentangled representation learning and reconstruction quality since the model does not have enough capacity to learn correlated latent variables that capture detail information present in most image data. To overcome this trade-off, we present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method; then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables, adding detail information while maintaining conditioning on the previously learned disentangled factors. Taken together, our multi-stage modelling approach results in a single, coherent probabilistic model that is theoretically justified by the principal of D-separation and can be realized with a variety of model classes including likelihood-based models such as variational autoencoders, implicit models such as generative adversarial networks, and tractable models like normalizing flows or mixtures of Gaussians. We demonstrate that our multi-stage model has higher reconstruction quality than current state-of-the-art methods with equivalent disentanglement performance across multiple standard benchmarks. In addition, we apply the multi-stage model to generate synthetic tabular datasets, showcasing an enhanced performance over benchmark models across a variety of metrics. The interpretability analysis further indicates that the multi-stage model can effectively uncover distinct and meaningful features of variations from which the original distribution can be recovered.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
