Investigating Natural and Artificial Dynamics in Graph Data Mining and Machine Learning

The complexity of relationships between entities is increasing in the era of big data, leading to a growing interest in graph (network) data, owing to its ability to encode intricate relational information. Graph data mining and machine learning methods extract informative node and graph representations to support broad applications, which have been proven effective for various high-impact tasks in the fields such as computer vision, natural language processing, and recommendation systems. Despite their effectiveness, graph data mining and machine learning methods face practical challenges in real-world scenarios. First, the input graphs may change over time, making it necessary to integrate time-evolving information to enhance representation capabilities. Second, the input graphs may contain unreliable, noisy, or sub-optimal information, requiring researchers and practitioners to intentionally modify the graph topology and node features to improve downstream performance. Facing these two phenomena, our research works focus on natural and artificial dynamics for benefiting graph data mining and machine learning. In this paper, we will briefly introduce our recent works in investigative natural and artificial dynamics and point out some under-explored research problems in the interaction of these dynamics.