Timezone: »

 
Poster
Multi-task Learning of Order-Consistent Causal Graphs
Xinshi Chen · Haoran Sun · Caleb Ellington · Eric Xing · Le Song

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @
in Poster Session 4 »
We consider the problem of discovering $K$ related Gaussian directed acyclic graphs (DAGs), where the involved graph structures share a consistent causal order and sparse unions of supports. Under the multi-task learning setting, we propose a $l_1/l_2$-regularized maximum likelihood estimator (MLE) for learning $K$ linear structural equation models. We theoretically show that the joint estimator, by leveraging data across related tasks, can achieve a better sample complexity for recovering the causal order (or topological order) than separate estimations. Moreover, the joint estimator is able to recover non-identifiable DAGs, by estimating them together with some identifiable DAGs. Lastly, our analysis also shows the consistency of union support recovery of the structures. To allow practical implementation, we design a continuous optimization problem whose optimizer is the same as the joint estimator and can be approximated efficiently by an iterative algorithm. We validate the theoretical analysis and the effectiveness of the joint estimator in experiments.
Keywords: Theory · Optimization · Graph Learning · Causality

Author Information

Xinshi Chen (Georgia Institution of Technology)
Haoran Sun (Georgia Institute of Technology)
Caleb Ellington (Carnegie Mellon University)
Eric Xing (Petuum Inc. / Carnegie Mellon University)
Le Song (Georgia Institute of Technology)

More from the Same Authors