Online Multi-Hop Information Based Kernel Learning Over Graphs

With complex systems emerging in various applications, e.g., financial, biological and social networks, graphs become working horse to model and analyse these systems. Nodes within networks usually entail attributes. Due to privacy concerns and missing observations, nodal attributes may be unavailable for some nodes in real-world networks. Besides, new nodes with unknown nodal attributes may emerge at any time, which require evaluation of the corresponding attributes in real-time. In this context, the present paper reconstructs nodal attributes of unobserved ones via an estimated nodal function based on their connectivity patterns with other nodes in the graph. Unlike existing works which only consider single-hop neighbors, the present paper further explores global information and adaptively combines the effects of multi-hop neighbors together. A multikernel-based approach is developed, which is capable of leveraging global network information, and scales well with network size as well. In addition, it has the flexibility to account for different nonlinear relationship by adaptively selecting the appropriate kernel combination. Experiments on real-word datasets corroborate the merits of the proposed algorithm.