Discovering Temporal Causal Relations from Subsampled Data

By Mingming Gong, Kun Zhang, Bernhard Schölkopf, Dacheng Tao, Philipp Geiger. 2015

97 citations recorded by the source corpus.

Subfields: Causal Inference & Discovery, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Causal Inference & Discovery

In Time-Series & Forecasting

Citations in the corpus

Causal Discovery from Heterogeneous/Nonstationary Data (2019, background): “, dynamic systems with insufficient time resolution, there may exist both instantaneous and time-lagged causal relationships over the measured data (Hyvärinen et al., 2010; Gong* et al., 2015).”
Causal Discovery from Temporally Aggregated Time Series (2017, methodology): “Following (Gong et al., 2015), we assume that the high-frequency data follow a VAR model, the error terms are non-Gaussian, and there are no confounders (Geiger et al.”
Invariant Causal Prediction for Sequential Data (2017, background): “r line of work starts from high-frequency data sampled from a Granger model without instantaneous eﬀects and tries to infer the instantaneous eﬀects appearing in low-frequency sub-sampled data (e.g., Gong et al., 2015; Tank et al., 2017). A further related area of research extends non-instantaneous ”
Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models (2019, background): “However, in practice, it is often the case that some causal interactions occur in the same time period, and thus it is important to consider contemporaneous causal relations, especially in time series with low temporal resolutions (Hyvärinen et al., 2010; Gong* et al., 2015), in aggregated data (Gon”
Rate-Agnostic (Causal) Structure Learning (2015, background): “The problem of causal learning from “undersampled” time series data was explicitly addressed by [6, 7], but they assumed that the degree of undersampling—i.”
A Survey of Learning Causality with Data (2018, background): “hat only a low-resolution version of the original time series is available, for example, we only observe the time series every k time steps [131]. The key assumption for the recently proposed methods [47, 63, 110] is that there exists a true timescale or causal frequency at which we can discover pro”
Review of Causal Discovery Methods Based on Graphical Models (2019, methodology): “It is well-established that the most common procedure, Granger causality, is very sensitive to temporal aggregation or subsampling [for the effect of aggregation and subsampling and some possible ways to deal with them, see (Danks and Plis, 2013; Gong* et al., 2015; Gong et al., 2017)].”
Causal Discovery from Subsampled Time Series Data by Constraint Optimization (2016, methodology): “Keywords: causality; causal discovery; graphical models; time series; constraint satisfaction; constraint optimization.”
Granger Causality: A Review and Recent Advances (2021, methodology): “In Section 4.3, we review recent approaches to identifying Granger causality in subsampled and mixed frequency time series (Gong et al., 2015; Tank et al., 2019).”
DYNOTEARS: Structure Learning from Time-Series Data (2020, unknown): “See for example Gong et al. (2015); Hyttinen et al. (2016); Plis et al. (2015); Cook et al. (2017).”
Causal Discovery and Inference: Concepts and Recent Methodological Advances (2016, background): “…pre-sent the theoretical results which make it possible to discover the temporal causal relations at the true causal frequency from subsampled data (Gong et al. 2015), that is, one can recover monthly causal relations from quarterly data or estimate rapid causal influences between stocks from…”
A Survey of Learning Causality with Data: Problems and Methods (2018, background): “The key assumption for the recently proposed methods [47, 63, 110] is that there exists a true timescale or causal frequency at which we can discover proper causal graph structures with the highest confidence [33].”