Learning from Contagion (Without Timestamps)
نویسندگان
چکیده
We introduce and study new models for learning from contagion processes in a network. A learning algorithm is allowed to either choose or passively observe an initial set of seed infections. This seed set then induces a final set of infections resulting from the underlying stochastic contagion dynamics. Our models differ from prior work in that detailed vertex-byvertex timestamps for the spread of the contagion are not observed. The goal of learning is to infer the unknown network structure. Our main theoretical results are efficient and provably correct algorithms for exactly learning trees. We provide empirical evidence that our algorithm performs well more generally on realistic sparse graphs.
منابع مشابه
Locating Contagion Sources in Networks with Partial Timestamps
This paper studies the problem of identifying the contagion source when partial timestamps of a contagion process are available. We formulate the source localization problem as a ranking problem on graphs, where infected nodes are ranked according to their likelihood of being the source. Two ranking algorithms, cost-based ranking (CR) and tree-based ranking (TR), are proposed in this paper. Exp...
متن کاملHypothesis-Based Investigation of Digital Timestamps
Timestamps stored on digital media play an important role in digital investigations. Unfortunately, timestamps may be manipulated, and also refer to a clock that can be erroneous, failing or maladjusted. This reduces the evidentiary value of timestamps. This paper takes the approach that historical adjustments to a clock can be hypothesized in a clock hypothesis. Clock hypotheses can then be te...
متن کاملStatistical Tests for Contagion in Observational Social Network Studies
Current tests for contagion in social network studies are vulnerable to the confounding effects of latent homophily (i.e., ties form preferentially between individuals with similar hidden traits). We demonstrate a general method to lower bound the strength of causal effects in observational social network studies, even in the presence of arbitrary, unobserved individual traits. Our tests requir...
متن کاملInnovation Diffusion in Heterogeneous Populations: Contagion, Social Influence, and Social Learning By
New ideas, products, and practices take time to diffuse, a fact that is often attributed to some form of heterogeneity among potential adopters. This paper examines three broad classes of diffusion models -contagion, social influence, and social learning – and shows how to incorporate heterogeneity into each at a high level of generality without losing analytical tractability. Each type of mode...
متن کاملLearning to Forget? Contagion and Political Risk in Brazil
We examine whether Brazilian sovereign spreads of over 20 percent in 2002 could be due to contagion from Argentina or to domestic politics, or both. Treating unilateral debt restructuring as a policy variable gives rise to the possibility of self-fulfilling crisis, which can be triggered by contagion. We explore an alternative political-economy explanation of panic in financial markets inspired...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014