Graphs have a superior ability to represent relational data, such as chemical compounds,
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …

Semi-supervised clustering leverages prior information in the form of constraints to achieve
higher-quality clustering outcomes. However, most existing methods struggle with large …

Graph generation plays a vital role in a wide range of applications such as traffic analysis,
drug discovery and more, for its rapid and efficient generation speed coupled with its precise …

Probabilistic embeddings have several advantages over deterministic embeddings as they
map each data point to a distribution, which better describes the uncertainty and complexity …

Transformers demonstrate significant advantages as the building block of modern LLMs. In
this work, we study the capacities of Transformers in performing unsupervised learning. We …

Graph neural networks (GNNs) have become the dominant solution for learning on graphs,
the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial …

Community detection is a critical task in graph theory, social network analysis, and
bioinformatics, where communities are defined as clusters of densely interconnected nodes …

With the rapid advancement of large language models (LLMs), discrete speech
representations have become crucial for integrating speech into LLMs. Existing methods for …

The vast, complex, and dynamic nature of social message data has posed challenges to
social event detection (SED). Despite considerable effort, these challenges persist, often …

Superpixel segmentation is a foundation for many higher-level computer vision tasks, such
as image segmentation, object recognition, and scene understanding. Existing graph-based …