Recent years have witnessed a dramatic increase in graph applications due to advancements in information and communication technologies. In various applications, such as social networks, communication networks, the internet of things (IOTs), and human disease networks, graph data contains rich information and exhibits diverse characteristics. Specifically, graph data may come with the node or edge attributes showing the property of an entity or a connection, arise with signed or unsigned edges indicating the positive or negative relationships, form homogeneous or heterogeneous information networks modeling different scenarios and settings. Furthermore, in these applications, graph data is evolving and expanding more and more dynamically. The diverse, dynamic, and large-scale nature of graph data requires different data mining techniques and advanced machine learning methods. Meanwhile, the computing system evolves rapidly and becomes large-scale, collaborative, and distributed, with many computing principles proposed such as cloud computing, edge computing, and federated learning [1]. Learning from big graph data in future-generation computing systems considers the effectiveness of graph learning [2], scalability of large-scale computing, privacy-preserving under the federated computing setting with multi-source graphs, and graph dynamics in the distributed environment. Today’s researchers have realized that novel graph learning theory, big graph-specific platforms, and advanced graph processing techniques are needed. Therefore, a set of research topics such as knowledge graph reasoning [3], graph self-supervised learning [4], temporal graph modeling [5], and graph embedding techniques [6], [7] has emerged, and applications such as graph-based anomaly detection [8], [9], community detection [10], social recommendation, social influence analytics are becoming important issues for the research community.