论文标题
可交换的神经颂歌用于设置建模
Exchangeable Neural ODE for Set Modeling
论文作者
论文摘要
通过一组向量组成的实例推理，例如点云，要求一个元素之间的内部依赖性特征。但是，由于这些实例是无序的，因此当输入的顺序排列时，元素的特征应保持不变。对于大多数神经体系结构，该属性置换量比是一个具有挑战性的限制。尽管最近的工作提出了全球汇集和基于注意力的解决方案，但这些解决方案可能会受到限制在实践中捕获的方式。在这项工作中，我们提出了一种更通用的公式，以通过普通的微分方程（ODE）实现置换量比。我们提出的模块可交换的神经颂歌（ExNode）可以无缝地应用于判别和生成任务。我们还将设置建模扩展到时间维度，并为时间集建模提出了基于VAE的模型。广泛的实验证明了我们方法对强基础的功效。
Reasoning over an instance composed of a set of vectors, like a point cloud, requires that one accounts for intra-set dependent features among elements. However, since such instances are unordered, the elements' features should remain unchanged when the input's order is permuted. This property, permutation equivariance, is a challenging constraint for most neural architectures. While recent work has proposed global pooling and attention-based solutions, these may be limited in the way that intradependencies are captured in practice. In this work we propose a more general formulation to achieve permutation equivariance through ordinary differential equations (ODE). Our proposed module, Exchangeable Neural ODE (ExNODE), can be seamlessly applied for both discriminative and generative tasks. We also extend set modeling in the temporal dimension and propose a VAE based model for temporal set modeling. Extensive experiments demonstrate the efficacy of our method over strong baselines.
