Titlebook: Neural Information Processing; 28th International C Teddy Mantoro,Minho Lee,Achmad Nizar Hidayanto Conference proceedings 2021 Springer Nat

ensemble

PathSAGE: Spatial Graph Attention Neural Networks with Random Path Samplingused in CCNs to extract deeper features of Euclidean structure data. However, for non-Euclidean structure data, too deep GCNs will confront with problems like “neighbor explosion” and “over-smoothing”, it also cannot be applied to large datasets. To address these problems, we propose a model called

LURE

Label Preserved Heterogeneous Network Embeddingand effectiveness. However, the rich node label information is not considered by these HNE methods, which leads to suboptimal node embeddings. In this paper, we propose a novel .abel .reserved .eterogeneous .etwork .mbedding (LPHNE) method to tackle this problem. Briefly, for each type of the nodes,

esoteric

Spatio-Temporal Dynamic Multi-graph Attention Network for Ride-Hailing Demand Predictionthe complicated Spatio-temporal correlations. Existing methods mainly focus on modeling the Euclidean correlations among spatially adjacent regions and modeling the non-Euclidean correlations among distant regions through the similarities of features such as points of interest (POI). However, due to

palette

An Implicit Learning Approach for Solving the Nurse Scheduling Problem consists in building weekly schedules by assigning nurses to shift patterns, such that workload constraints are satisfied, while nurses’ preferences are maximized. In addition to the difficulty to tackle this NP-hard problem, extracting the problem constraints and preferences from an expert can be

Grandstand

Improving Goal-Oriented Visual Dialogue by Asking Fewer Questionsarticular, goal-oriented visual dialogue, which locates an object of interest from a group of visually presented objects by asking verbal questions, must be able to efficiently narrow down and identify objects through question generation. Several models based on GuessWhat?! and CLEVR Ask have been p

分贝

Generator

利用

Hamper

Multi-view Fractional Deep Canonical Correlation Analysis for Subspace Clusteringionship and learn from more than two views. In addition, real-world data sets often contain much noise, which makes the performance of machine learning algorithms degraded. This paper presents a multi-view fractional deep CCA (MFDCCA) method for representation learning and clustering tasks. The prop

Custodian

LSMVC:Low-rank Semi-supervised Multi-view Clustering for Special Equipment Safety Warningre based on the Alternating Direction Method of Multipliers. Finally, experiments are carried out on six real datasets including the Elevator dataset, which is collected from the actual work. The results show that the proposed clustering method can achieve better clustering performance than other clustering method.