基于跨域潜在同调的终身解纠缠表示学习
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
摘要：
现实世界中的智能行为需要从一系列持续的经验中获取新知识的能力，同时保留和重用过去的知识。我们提出了一种新的算法，用于从逐段静态视觉数据中进行无监督的表示学习：具有共享嵌入的变分自编码器（VASE）。基于最小描述长度原则，VASE自动检测数据分布中的变化，并为新知识分配空闲的表示容量，同时保护先前学习的表示免受灾难性遗忘。我们的方法鼓励学习的表示被解开，这赋予了一些理想的属性：VASE可以明智地处理模糊的输入，它可以通过基于解释的探索来增强自己的表示，最重要的是，它表现出语义上有意义的共享不同数据集之间的潜伏期。与具有纠缠表示的基线相比，我们的方法能够超越表面级统计数据进行推理，并执行语义上有意义的跨域推理。
英文摘要：
Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoencoder with Shared Embeddings (VASE). Based on the Minimum Description Length principle, VASE automatically detects shifts in the data distribution and allocates spare representational capacity to new knowledge, while simultaneously protecting previously learnt representations from catastrophic forgetting. Our approach encourages the learnt representations to be disentangled, which imparts a number of desirable properties: VASE can deal sensibly with ambiguous inputs, it can enhance its own representations through imagination-based exploration, and most importantly, it exhibits semantically meaningful sharing of latents between different datasets. Compared to baselines with entangled representations, our approach is able to reason beyond surface-level statistics and perform semantically meaningful cross-domain inference.
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。
