{ "id": "2003.04078", "version": "v1", "published": "2020-03-09T12:37:40.000Z", "updated": "2020-03-09T12:37:40.000Z", "title": "A Survey on The Expressive Power of Graph Neural Networks", "authors": [ "Ryoma Sato" ], "comment": "41 pages", "categories": [ "cs.LG", "stat.ML" ], "abstract": "Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have been revealed recently. Consequently, many GNN models have been proposed to overcome these limitations. In this survey, we provide a comprehensive overview of the expressive power of GNNs and provably powerful variants of GNNs.", "revisions": [ { "version": "v1", "updated": "2020-03-09T12:37:40.000Z" } ], "analyses": { "keywords": [ "graph neural networks", "expressive power", "effective machine learning models", "graph learning problems", "gnn models" ], "note": { "typesetting": "TeX", "pages": 41, "language": "en", "license": "arXiv", "status": "editable" } } }