Search Results

The anchor graph-based multi-view subspace clustering (MVSC) methods have shown promising performance when dealing with large-scale data. However, the consistent information is not fully explored when learning anchor graphs and exploring higher-...

Incomplete multi-view clustering (IMVC) has attracted much attention due to its superior performance in handling incomplete multi-view data. However, existing IMVC methods pay little attention to the semantic associations between incomplete data ...

Most previous unsupervised multi-view feature selection (UMFS) methods have achieved appealing performance by exploring the consistency among multiple views. However, they have the following shortcomings: (1) They often fail to consider the ...

Temporal motifs are recurring subgraph patterns in temporal graphs, and are present in various domains such as social networks, fraud detection, and biological networks. Despite their significance, counting temporal motifs efficiently remains a challenge,...

Trajectory similarity computation is a fundamental problem in various applications (e.g., transportation optimization, behavioral study). Recent researches learn trajectory representations instead of point matching to realize more accurate and efficient ...

Subspace learning-based methods have shown excellent performance for multi-view clustering, yet have the following problems: (1) most existing methods obtain the subspace representation from the original space, which might contain noises and ...

• We propose a novel multi-view self-representation method for clustering.
• The consistency and diversity of representation are fully exploited.
• The Schatten p-norm is used to constrain the consistent coefficient matrix.
• We ...

In comparison to numerical ratings and implicit feedback, textual reviews offer a deeper understanding of user preferences and item attributes. Recent research underscores the potential of reviews in augmenting recommendation capabilities, thereby ...

Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learning tasks, particularly for training a deep neural network. Recently, a ...

In recent years, the fusion of graph convolutional networks (GCNs) with contrastive learning (CL) has emerged as a promising approach in recommender systems, owing to its adeptness in extracting self-supervised signals from the original data, thus ...

Inferring social relationships from human mobility data holds significant value in real-life spatio-temporal applications, inspiring the development of a series of graph-based methods for deriving such relationships. However, despite their noted ...

Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous graph data, ranging from link prediction to node classification. However, most existing works ignore the relation ...

Next location recommendation plays an important role in various location-based services, yielding great value for both users and service providers. Existing methods usually model temporal dependencies with explicit time intervals or learn representation ...

Deep learning (DL) has shown great potential in enhancing the performance of traditional numerical weather prediction (NWP) methods in weather forecasting. Certain applications such as wind power generation desire more accurate wind predictions ...

• A novel heterogeneous neural network for wind forecasting.
• A target variable transformation based on meteorological domain knowledge.
• A time-related embedding technique and a novel loss function to improve model generalization.

Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking different trajectories to users with the exploration of complex mobility patterns. Existing works mainly rely on the recurrent neural framework to encode the temporal ...

As a challenging task in the field of unsupervised learning, incomplete multi-view clustering can fully utilize multi-view information in the absence of partial views. Nevertheless, most existing methods still suffer from the following two ...

• We propose a tensor-based incomplete multi-view clustering framework.
• The missing views are reconstructed based on NMF and self-representation.
• The tensor low-rank is imposed on the self-representation of all views.
• We present ...

Trajectory representation learning aims to embed trajectory sequences into fixed-length vector representations while preserving their original spatio-temporal feature proximity. Existing works either learn trajectory representations for specific ...

• A self-supervised trajectory representation learning framework is proposed.
• Three well-designed loss functions are proposed to jointly optimize the model.
• Three downstream tasks are performed to verify the effect of the proposed ...

Traffic forecasting is a critical service in Intelligent Transportation Systems (ITS). Utilizing deep models to tackle this task relies heavily on data from traffic sensors or vehicle devices, while some cities might lack device support and thus have few ...

Anomaly detection on multivariate time series (MTS) is of great importance in both data mining research and industrial applications. While a handful of anomaly detection models are developed for MTS data, most of them either ignore the potential ...

Heterogeneous Graph Embedding (HGE) is receiving a great attention from researchers, as it can be widely and effectively used to solve problems from various real-world applications. The existing HGE models mainly learn node representation ...

• We present a novel method named OSGNN.
• It considers both local and higher-order information of heterogeneous graphs.
• We conduct experiments and compare the performance with 8 competitive baselines.

Heterogeneous graph neural networks have gained great popularity in tackling various network analysis tasks on heterogeneous network data. However, most existing works mainly focus on general heterogeneous networks, and assume that there is only one ...