{"url":"/method/appnp","slug":"appnp","name":"APPNP","full_name":"Approximation of Personalized Propagation of Neural Predictions","full_name_withheld":false,"description_markdown":"Neural message-passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighbourhood is hard to extend. This paper uses the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank. We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP. Our model's training time is on par or faster and its number of parameters is on par or lower than previous models. It leverages a large, adjustable neighbourhood for classification and can be easily combined with any neural network. We show that this model outperforms several recently proposed methods for semi-supervised classification in the most thorough study done so far for GCN-like models.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","paper":"/paper/predict-then-propagate-graph-neural-networks","first_author":"Johannes Gasteiger","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/predict-then-propagate-graph-neural-networks"},"source":{"url":"https://arxiv.org/abs/1810.05997v6","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Representation Learning","url":"/methods/category/graph-representation-learning","pwc_aliases":[]}],"n_papers_tagged":9,"archive_num_papers":9,"papers_newest_first":[{"paper":"/paper/lightgcn-evaluated-and-enhanced","title":"LightGCN: Evaluated and Enhanced","date":"2023-12-17","arxiv_id":"2312.16183","n_code_links":1,"syntology":null},{"paper":null,"title":"Understanding and Improving Deep Graph Neural Networks: A Probabilistic Graphical Model Perspective","date":"2023-01-25","arxiv_id":"2301.10536","n_code_links":0,"syntology":null},{"paper":null,"title":"Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework","date":"2023-01-11","arxiv_id":"2301.04318","n_code_links":0,"syntology":null},{"paper":"/paper/mgdcf-distance-learning-via-markov-graph","title":"MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering","date":"2022-04-05","arxiv_id":"2204.02338","n_code_links":2,"syntology":null},{"paper":"/paper/extract-the-knowledge-of-graph-neural","title":"Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework","date":"2021-03-04","arxiv_id":"2103.02885","n_code_links":1,"syntology":{"ran":2,"of":3,"unverified":1,"pointer_only":3}},{"paper":"/paper/on-the-equivalence-of-decoupled-graph","title":"On the Equivalence of Decoupled Graph Convolution Network and Label Propagation","date":"2020-10-23","arxiv_id":"2010.12408","n_code_links":1,"syntology":{"ran":0,"of":4,"unverified":4,"pointer_only":0}},{"paper":"/paper/a-unified-view-on-graph-neural-networks-as-1","title":"A Unified View on Graph Neural Networks as Graph Signal Denoising","date":"2020-10-05","arxiv_id":"2010.01777","n_code_links":1,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":null,"title":"Tackling Over-Smoothing for General Graph Convolutional Networks","date":"2020-08-22","arxiv_id":"2008.09864","n_code_links":0,"syntology":null},{"paper":"/paper/predict-then-propagate-graph-neural-networks","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","date":"2018-10-14","arxiv_id":"1810.05997","n_code_links":5,"syntology":{"ran":1,"of":12,"unverified":11,"pointer_only":0}}],"papers_shown":9,"tasks":[{"task":"/task/node-classification","name":"Node Classification","papers":4},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":2},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/graph-classification","name":"Graph Classification","papers":1},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/multi-modal-recommendation","name":"Multi-modal Recommendation","papers":1},{"task":"/task/node-classification-on-non-homophilic","name":"Node Classification on Non-Homophilic (Heterophilic) Graphs","papers":1},{"task":"/task/pseudo-label","name":"Pseudo Label","papers":1},{"task":"/task/variational-inference","name":"Variational Inference","papers":1}],"tasks_shown":14,"n_tasks":14,"usage_by_year":[{"year":"2018","papers":1},{"year":"2020","papers":3},{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/appnp"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}