Скачать с ютуб Relating Graph Neural Networks to Structural Causal Model | Matej Zečević в хорошем качестве

Relating Graph Neural Networks to Structural Causal Model | Matej Zečević

Join the Learning on Graphs and Geometry Reading Group: https://hannes-stark.com/logag-readin... Paper "Relating Graph Neural Networks to Structural Causal Models": https://arxiv.org/pdf/2109.04173.pdf Abstract: Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations. For most processes of interest the underlying SCM will only be partially observable, thus causal inference tries to leverage any exposed information. Graph neural networks (GNN) as universal approximators on structured input pose a viable candidate for causal learning, suggesting a tighter integration with SCM. To this effect we present a theoretical analysis from first principles that establishes a novel connection between GNN and SCM while providing an extended view on general neural-causal models. We then establish a new model class for GNN-based causal inference that is necessary and sufficient for causal effect identification. Our empirical illustration on simulations and standard benchmarks validate our theoretical proofs. Authors: Matej Zečević, Devendra Singh Dhami, Petar Veličković, Kristian Kersting Links: Twitter Hannes:   / hannesstaerk   Twitter Dominique:   / dom_beaini   Twitter Valence Discovery:   / valence_ai   Reading Group Slack: https://join.slack.com/t/logag/shared... ~ 00:00 Introduction 01:13 Towards Neuro-Causality intro 25:28 GNN-Based Causal Inference 48:35 Identifiability & Estimation 59:55 Causality for Machine Learning 1:04:20 Q&A