In this paper, we present Conjoint Attentions (CAs), a class of novel learning-to-attend strategies for graph neural networks (GNNs). Besides considering the layer-wise node features propagated within the GNN, CAs can additionally incorporate various structural interventions, such as node cluster embedding, and higher-order structural correlations that can be learned outside of GNN, when computing attention scores. The node features that are regarded as significant by the conjoint criteria are therefore more likely to be propagated in the GNN. Given the novel Conjoint Attention strategies, we then propose Graph conjoint attention networks (CATs) that can learn representations embedded with significant latent features deemed by the Conjoint Attentions. Besides, we theoretically validate the discriminative capacity of CATs. CATs utilizing the proposed Conjoint Attention strategies have been extensively tested in well-established benchmarking datasets and comprehensively compared with state-of-the-art baselines. The obtained notable performance demonstrates the effectiveness of the proposed Conjoint Attentions.
COOL: A Conjoint Perspective on Spatio-Temporal Graph Neural Network for Traffic Forecasting
School of Statistics and Data Science, Nankai University(南开大学统计与数据科学学院);University of California(加利福尼亚大学);Yale School of Medicine(耶鲁医学院);Yale School of Public Health(耶鲁公共卫生学院)
AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations
University of Konstanz(康斯坦茨大学)
本文介绍了注意隐式表示网络(AIR-Nets),这是一种简单但高效的点云三维重建架构。由于以局部和模块化方式表示3D形状可以提高泛化和重建质量,因此AIR-Nets将输入点云编码为一组锚定在3D空间中的局部潜在向量,这些向量局部描述对象的几何形状,以及全局潜在描述,从而实现全局一致性。我们的模型是第一个无网格的,基于编码器的方法,局部描述了一个隐式函数。来自[Zhao et al. 2020]的向量注意力机制作为主要的点云处理模块,并允许排列不变性和平移等变性。当用3D坐标查询时,我们的解码器从全局和附近的局部隐向量中收集信息,以预测占用值。ShapeNet数据集上的实验表明,AIR-Nets的性能明显优于以前最先进的基于编码器的隐式形状学习方法,尤其是在稀疏设置中占主导地位。此外,我们的模型在zero-shot设置中很好地推广到FAUST数据集。最后,由于AIR-Nets使用稀疏的潜在表示并遵循简单的操作方案,因此该模型为未来的工作提供了几个现有的途径。我们的代码可在https://github.com/SimonGiebenhain/AIR-Nets上获得。
AnomalousNet: A Hybrid Approach with Attention U-Nets and Change Point Detection for Accurate Characterization of Anomalous Diffusion in Video Data
Instituto Universitario de Matemática Pura y Aplicada (IUMPA), Universitat Politècnica de València(瓦伦西亚理工大学纯数学与应用数学大学研究所);Centro de Investigación en Gestión e Ingeniería de Producción (CIGIP), Universitat Politècnica de València(瓦伦西亚理工大学生产管理与工程研究中心)
Mutually Causal Semantic Distillation Network for Zero-Shot Learning
Huazhong University of Science and Technology(华中科技大学);National Anti-Counterfeit Engineering Research Center(国家防伪工程技术研究中心);Nanjing University of Science and Technology(南京理工大学)
Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results
Center for Frontier AI Research(前沿人工智能研究中心);Agency for Science, Technology, and Research(新加坡科技研究局);Institute for High Performance Computing(高性能计算研究所);Nanyang Technological University(南洋理工大学);Singapore Institute of Manufacturing Technology(新加坡制造技术研究所)