Explainability and Graph Learning from Social Interactions

원문 초록

Social learning algorithms provide models for the formation of opinions over social networks resulting from local reasoning and peer-to-peer exchanges. Interactions occur over an underlying graph topology, which describes the flow of information among the agents. To account for drifting conditions in the environment, this work adopts an adaptive social learning strategy, which is able to track variations in the underlying signal statistics. Among other results, we propose a technique that addresses questions of explainability and interpretability of the results when the graph is hidden. Given observations of the evolution of the beliefs over time, we aim to infer the underlying graph topology, discover pairwise influences between the agents, and identify significant trajectories in the network. The proposed framework is online in nature and can adapt dynamically to changes in the graph topology or the true hypothesis.