Fair attribution of functional contribution in artificial and biological networks

Alon Keinan*, Ben Sandbank, Claus C. Hilgetag, Isaac Meilijson, Eytan Ruppin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


This letter presents the multi-perturbation Shapley value analysis (MSA), an axiomatic, scalable, and rigorous method for deducing causal function localization from multiple perturbations data. The MSA, based on fundamental concepts from game theory, accurately quantifies the contributions of network elements and their interactions, overcoming several shortcomings of previous function localization approaches. Its successful operation is demonstrated in both the analysis of a neurophysiological model and of reversible deactivation data. The MSA has a wide range of potential applications, including the analysis of reversible deactivation experiments, neuronal laser ablations, and transcranial magnetic stimulation "virtual lesions," as well as in providing insight into the inner workings of computational models of neurophysiological systems.

Original languageEnglish
Pages (from-to)1887-1915
Number of pages29
JournalNeural Computation
Issue number9
StatePublished - Sep 2004


Dive into the research topics of 'Fair attribution of functional contribution in artificial and biological networks'. Together they form a unique fingerprint.

Cite this