2021/10/20 by Alejandro de la Concha, de la Concha, Alejandro, Argyris Kalogeratos +3
Psychology · Computer Science · Biochemistry, Genetics and Molecular Biology · #Mental Health Research Topics #Data Stream Mining Techniques #Gene Regulatory Network Analysis
paper · pdf · doi:10.48550/arxiv.2110.10518
Consider a heterogeneous data stream being generated by the nodes of a graph.\nThe data stream is in essence composed by multiple streams, possibly of\ndifferent nature that depends on each node. At a given moment \τ, a\nchange-point occurs for a subset of nodes C, signifying the change in the\nprobability distribution of their associated streams. In this paper we propose\nan online non-parametric method to infer \τ based on the direct estimation\nof the likelihood-ratio between the post-change and the pre-change distribution\nassociated with the data stream of each node. We propose a kernel-based method,\nunder the hypothesis that connected nodes of the graph are expected to have\nsimilar likelihood-ratio estimates when there is no change-point. We\ndemonstrate the quality of our method on synthetic experiments and real-world\napplications.\n