Root Cause Analysis of Outliers in Unknown Cyclic Graphs
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:MNXAXAGTrecord.jsonopen to challenge →
read the original abstract
We study the propagation of outliers in cyclic causal graphs with linear structural equations, tracing them back to one or several "root cause" nodes. We show that it is possible to identify a short list of potential root causes provided that the perturbation is sufficiently strong and propagates according to the same structural equations as in the normal mode. This shortlist consists of the true root causes together with those of its parents lying on a cycle with the root cause. Notably, our method does not require prior knowledge of the causal graph and yields encouraging results on simulated data and real data from biology and cloud computing.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
PRIM: Meta-Learned Bayesian Root Cause Analysis
PRIM is a meta-learned Bayesian RCA method that marginalizes structural uncertainty via a MACE transformer neural process for zero-shot inference on systems up to 100 variables.
-
PRIM: Meta-Learned Bayesian Root Cause Analysis
PRIM meta-learns a Model-Averaged Causal Estimation transformer to perform Bayesian RCA by marginalizing structural uncertainty over synthetic causal priors, achieving 17ms inference on systems up to 100 variables.
-
PRIM: Meta-Learned Bayesian Root Cause Analysis
PRIM is a meta-learned Bayesian RCA method that identifies root causes by averaging over many possible causal structures via a prior-fitted neural process, achieving 17 ms inference on systems up to 100 variables.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.