Online Intelligence and Trust Computation in Large-scale Dynamic Networks

View project on GitHub


Aim and Scope

The large-scale dynamic network modelling online social life is complex in data structure, rich in knowledge and challenging in intelligent computation.

The concept of trust has long been subjective in human social activities. Measuring trust is always challenging, yet intelligent computation enhancing especially in the context of online social network (OSN). The unique applicability of modelling both temporal and spatial aspects enables dynamic networks abstracting the world in a complex data structure of graph. With the base units of a static graph, vast number of cases of combinations of nodes and edges illustrate the interactions of the real-world entities in the spatial aspect. For example, the nodes and edges represent the users and the various online social activities in a snapshot of OSN. Under the evolving graph structures, the evolutional patterns represent rich information from the temporal side. Meanwhile, the multimedia contents, e.g., natural language, images and video, denoted as the attributes of the graph entities, increase the difficulties of graph learning.

Intelligent methods have been dramatically developed in recent years. Supported by deep neural networks, graph machine learning tends to explain the dynamics either in network topologies or entity attributions. Moreover, interdisciplinary approaches of intelligent computation on trust help graph machine learning understand the complex and dynamically changing networks, target fast relevant topologies and attributes, and return more accurate predictions.

The special session aims to solicit contributions in intelligent computational frameworks, models, algorithms and applications for quantifying trust of online activities on the large-scale dynamic networks.


  • Supervised / semi-supervised / unsupervised graph machine learning
  • Deep neural network with input of graph structured data
  • Network pattern recognition
  • Dynamic graph embedding
  • Temporal attribute learning
  • Spatial and temporal data structure
  • Dynamic analysis in large-scale network
  • Large-scale hierarchical / heterogeneous information network
  • Temporal graph and graph matching within / across network(s)
  • Stochastic probability in dynamic graph mining
  • Time series learning over evolutional graph changes
  • Trust computation model in complex social network
  • Online trust learning, including trust propagation, causal reasoning, entity resolution, etc.
  • Other scenarios related to evolutional network topology and contextual attributed graph

Important Dates

  • Paper submission: January 31, 2022 (11:59 PM AoE) STRICT DEADLINE
  • Notification of acceptance: April 26, 2022
  • Final paper submission: May 23, 2022

Submission portal


Dr Shan Xue: School of Computing, Macquarie University
Prof Jian Yang: School of Computing, Macquarie University
Prof Amin Beheshti: School of Computing, Macquarie University
Prof Quanzheng Sheng: School of Computing, Macquarie University