A New Look at Causal Independence

By David E. Heckerman, J. Breese. 1994

Heckerman (1993) defined causal independence in terms of a set of temporal conditional independence statements. These statements formalized certain types of causal interaction where (1) the effect is independent of the order that causes are introduced and (2) the impact of a single cause on the effect does not depend on what other causes have previously been applied. In this paper, we introduce art equivalent a temporal characterization of causal independence based on a functional representation of the relationship between causes and the effect. In this representation, the interaction between causes and effect can be written as a nested decomposition of functions. Causal independence can be exploited by representing this decomposition in the belief network, resulting in representations that are more efficient for inference than general causal models. We present empirical results showing the benefits of a causal-independence representation for belief-network inference.

How researchers see this paper

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

Citations in the corpus

Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms (2019, background): “Many researches have been devoted to improving the performance of network construction [30], [32], [33] and probabilistic inference in causal graphs [34], [35].”
A Causal Framework for Discovering and Removing Direct and Indirect Discrimination (2016, background): “Many researches have been devoted to improving the performance of network construction (Kalisch and B¨uhlmann 2007; Tsamardinos et al. 2003; Aliferis et al. 2010) and probabilistic inference in causal networks (Heckerman and Breese 1994; 1996).”
Bayesian Networks in Reliability: Some Recent Developments (2004, background): “Many researchers, including Heckerman and Breese (1994) and Boutilier et al. (1996), have explored even more cost-efficient representations.”
Learning Bayesian Networks with Local Structure (1996, methodology): “This is due to the fact that many of the CPTs in CTS and TJ are represented using noisy-or and noisy-max [Heckerman and Breese 1994], which can be better approximated by trees (rather than by default tables).”