Gated Graph Sequence Neural Networks
Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and modern optimization techniques and then extend to output sequences. The result is a flexible and broadly useful class of neural network models that has favorable inductive biases relative to purely sequence-based models (e.g., LSTMs) when the problem is graph-structured. We demonstrate the capabilities on some simple AI (bAbI) and graph algorithm learning tasks. We then show it achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures. Paper: http://arxiv.org/abs/1511.05493
Видео Gated Graph Sequence Neural Networks канала Microsoft Research
Видео Gated Graph Sequence Neural Networks канала Microsoft Research
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
The Intern Experience at Microsoft Research CambridgeDirections in ML: Taking Advantage of Randomness in Expensive Optimization ProblemsBattling Tuberculosis Using Microsoft TechnologyFast and Flexible Multi-Task Classification Using Conditional Neural Adaptive ProcessesSustainable Smart City SolutionsKeynote: Systems Research - Fueling Future DisruptionsData Visualization Reaches New Heights with LayerscapeProvably efficient reinforcement learning with Dr. Akshay Krishnamurthy | PodcastFaculty Summit 2018 IntroductionStructured light: seeing less to see more in optical microscopyAugmenting Visualization Tools with Automated Design & RecommendationGeek Heresy: Rescuing Social Change from the Cult of TechnologyModels as Code: Differentiable Programming with ZygoteImprovements on Higher Order Ambisonics ReproductionPlatform for Situated Intelligence Workshop | Day 1Cambridge lab overview with Chris BishopGet free cloud computing time and storage on Microsoft AzureAI Institute "Geometry of Deep Learning" 2019 [Workshop] Day 1 | Session 2System Design for Cloud Services - Part 1De-Identifying Healthcare Data for ResearchSmall Deep Neural Networks - Their Advantages, and Their Design