Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with features activating sparsely across different tasks and information being shared as appropriate. Importantly, we never directly observe the factors of variations but establish that access to multiple tasks is sufficient for identifiability under sufficiency and minimality assumptions. We validate our approach on six real world distribution shift benchmarks, and different data modalities (images, text), demonstrating how disentangled representations can be transferred to real settings.

翻译：从高维数据中恢复潜在变化因子先前主要集中于简单合成场景。先前工作大多基于无监督和弱监督目标，忽略了其对真实世界数据表示学习的积极影响。本研究提出利用从多样化监督任务集合中提取的知识来学习共同解耦表示。假设每个监督任务仅依赖于变化因子的未知子集，我们对监督多任务模型的特征空间进行解耦，使特征在不同任务间稀疏激活，并适当共享信息。重要的是，我们从未直接观测变化因子，但证明了在充分性与最小性假设下，多任务访问足以实现可辨识性。我们在六个真实世界分布偏移基准测试及不同数据模态（图像、文本）上验证了该方法，展示了解耦表示可迁移至真实场景。