In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector. Their unordered nature makes them suitable for modeling a wide variety of data, ranging from objects in images to point clouds to graphs. Deep learning has recently shown great success on other types of structured data, so we aim to build the necessary structures for sets into deep neural networks. The first focus of this thesis is the learning of better set representations (sets as input). Existing approaches have bottlenecks that prevent them from properly modeling relations between objects within the set. To address this issue, we develop a variety of techniques for different scenarios and show that alleviating the bottleneck leads to consistent improvements across many experiments. The second focus of this thesis is the prediction of sets (sets as output). Current approaches do not take the unordered nature of sets into account properly. We determine that this results in a problem that causes discontinuity issues with many set prediction tasks and prevents them from learning some extremely simple datasets. To avoid this problem, we develop two models that properly take the structure of sets into account. Various experiments show that our set prediction techniques can significantly benefit over existing approaches.
翻译:在此论文中,我们开发了与机器学习中的数据集合作的各种技巧。 每一个输入或输出都不是图像或序列, 而是一组: 一个没有顺序的多个对象的集合, 每个对象都是由特性矢量描述的。 它们没有顺序的性质使得它们适合于建模各种各样的数据, 从图像中的天体到点云层到图形。 深层次的学习最近在其他类型的结构化数据上显示了巨大的成功, 因此我们的目标是为各组建立必要的结构化结构进入深层的神经网络。 这个理论的第一个焦点是学习更精确的表达方式( 作为输入的设置) 。 现有的方法有瓶颈, 阻止它们正确建模集中对象之间的关系。 为了解决这个问题, 我们为不同的情景开发了各种各样的技术, 并表明减轻瓶颈可以导致许多实验的一致改进。 这个理论的第二个重点是对各组的预测( 设定为输出 ) 。 目前的方法并不适当地考虑到各组的不顺序化性质。 我们确定, 这个问题导致不连续的问题, 许多设定了预测任务, 并阻止它们学习一些极其简单的数据集。 为了避免这个模型, 我们设置了两个模型。 正确的计算出我们现有的方法。