Y
Yue Hu
Researcher at Chinese Academy of Sciences
Publications - 125
Citations - 1347
Yue Hu is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Question answering. The author has an hindex of 15, co-authored 93 publications receiving 673 citations. Previous affiliations of Yue Hu include Tianjin University.
Papers
More filters
Proceedings ArticleDOI
Graph Neural Architecture Search
TL;DR: Experiments on real-world datasets demonstrate that GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of validation set accuracy and in a transfer learning task, it is observed that graph neural architectures designed by GraphNAS, when transferred to new datasets, still gain improvement in Terms of prediction accuracy.
Posted Content
GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
TL;DR: A Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning, which first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks.
Proceedings Article
Social Recommendation with an Essential Preference Space
TL;DR: A novel social recommendation framework, called social recommendation with an essential preferences space (SREPS), which simultaneously models the structural information in the social network, the rating and the consumption Information in the recommender system under the capture of essential preference space is proposed.
Journal ArticleDOI
Cross-Modal Knowledge Reasoning for Knowledge-based Visual Question Answering
TL;DR: Inspired by the human cognition theory, this paper depicts an image by multiple knowledge graphs from the visual, semantic and factual views and re-formulates Knowledge-based Visual Question Answering as a recurrent reasoning process for obtaining complementary evidence from multimodal information.
Proceedings ArticleDOI
Collaborative Social Group Influence for Event Recommendation
TL;DR: A new Bayesian latent factor model SogBmf is proposed that combines social group influence and individual preference for event recommendation and demonstrates the effectiveness of the proposed method on real-world data sets.