Browse Proceedings

Accurate short-term forecasting of wind power generation is an effective way to ensure grid stability and rational dispatch. Although the transformer structure has made significant progress in the field of time series forecasting, its forecasting ...

With the rapid development of Geological Environment Remote Sensing (GERS) technology, accurately interpreting geological elements has become a critical task in the fields of geology and environmental science. To address the issue of low model ...

Time series data is increasingly prevalent in diverse sectors such as finance, IoT, and healthcare, with notable applications in neuroscience. Although neural networks exhibit proficiency in handling time series data, domain shift often impedes ...

Multivariate time series (MTS) anomaly detection is crucial for ensuring security and avoiding economic losses in various domains. Existing research based on the unified model’s information representation method have not adequately considered the ...

The problem of unsupervised anomaly detection in time series is very challenging. In recent years, deep learning based methods have been widely used. However, existing methods still struggle to effectively detect certain specific types of ...

Signed bipartite graphs differ from traditional graphs, which include two sets of nodes and signed edges. With the development of information technology, sign prediction in bipartite graphs has become a hotspot in both research and industrial ...

With the increasing popularity of online shopping platforms such as Amazon, Taobao and eBay, it is an urgent need to detect anomalous products, i.e., fake and illegal commodities. Heterogeneous graphs, which represent multiple types of objects and ...

Algorithms based on dense subgraphs have been proven to be highly effective in detecting financial risks, but their widespread use has been hampered by well-design density metrics and high-quality solution of densest subgraph problems. Considering ...

Attributed heterogeneous graph is widely utilized to model different types of objects and relationships in real world. Due to the capability of graph embedding in learning the effective features of nodes, the methods for attributed heterogeneous ...

Proper sample selection can better facilitate mutual information learning. Current sample selection methods suffer from fragile circularity, dependence on labeling information, and an imbalance in the volume of sample information. To address these ...

The detection and mitigation of fake news are critical to bolstering online security, upholding accurate knowledge, and safeguarding freedom of speech. Recent efforts have also focused on the structural properties of news propagation beyond the ...

Graph contrastive learning has improved graph representation learning, becoming a successful unsupervised graph representation learning method. This method first generates two or more views of the input graph through data augmentation and learns ...

With the rapid development of computer technology,the access to educational resources has become more and more convenient. Massive learning resources make it difficult for learners to reasonably organize the learning order of knowledge concepts. ...

In Graph Neural Networks, connectivity is usually represented by a fixed adjacency matrix, however, such a matrix fails to capture the complex entanglement present in relational data and is prone to the over-squashing and under-reaching issues. In ...

Stock movement prediction has long been an attractive task in financial data mining, with banks and investment institutions attracted by its wide range of applications and potentially high value. In contrast to the conventional time series ...

Fraud detection is a crucial data-mining task in the fields of finance and social media. Traditional machine-learning approaches predict risk based solely on the features of individual nodes. Recent advancements in graph-based methods allow for ...

Given a heterogeneous information network (HIN) $G$ and a query node $q$, community search (CS) over HINs aims to find a group of nodes containing the query node. However, we discover existing methodologies, such as $(k,\mathcal{P})$-core and $(k,\mathcal{P})$-truss, where $\mathcal{P}$ ...$\mathcal{}$$\mathcal{}$$\mathcal{}$

Community discovery is a crucial technique for extracting knowledge and patterns from social networks. Traditional algorithms for community discovery rely on the adjacency matrix, constructed from the neighbors of each node, to partition the nodes ...${}^{\mathrm{}}$

Topic modeling plays an important role in text mining for semantic mining. Existing topic models remain semantic loss, fuzzy topic concepts, and topic overlap issues because the sparsity of semantic information. For addressing above issues, in ...

Cohesive subgraph search in bipartite graphs has received much interest since the relationship between two different sets of objects in many applications can be modeled as a bipartite graph, such as ($\alpha$, $\beta$)-core, ($\alpha$, ${\beta )}_{\tau }$-core, and k-bitruss. ...$$${}_{}$$$$$$$$$$$$$$$$$

The happiness or regret based query has been another important tool in multi-dimensional decision-making besides the top-k and skyline queries. To avoid the happiness ratio being perceived as “made up” numbers which are often confused by users, we ...

How can we ensure that an information dissemination campaign reaches every corner of society and also achieves high overall reach? The problem of maximizing the spread of influence over a social network has commonly been considered with an ...

Graph edge coloring problem is a branch of the graph coloring problem and is a classic NP-hard problem in graph theory. The goal of edge coloring is to minimize the number of colors used for coloring such that any two adjacent edges are not the ...

With the expansion of extensive datasets of high-dimensional vectors, the approximate nearest neighbor search (ANNS) has become increasingly significant in data mining. Among the prevailing ANNS methods, graph-based methods achieve high recall at ...

In the realm of network, finding top-K influential vertices in data streams is a fundamental problem. Among these, Katz centrality serves as a valuable metric in the analysis of graph. Nevertheless, the computation of Katz centrality demands ...