{"url":"/method/dgi","slug":"dgi","name":"DGI","full_name":"Deep Graph Infomax","full_name_withheld":false,"description_markdown":"Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs—both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups.\r\n\r\nDescription and image from: [DEEP GRAPH INFOMAX](https://arxiv.org/pdf/1809.10341.pdf)","description_state":"present","introduced_year":null,"introduced_by":{"title":"Deep Graph Infomax","paper":"/paper/deep-graph-infomax","first_author":"Petar Veličković","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deep-graph-infomax"},"source":{"url":"http://arxiv.org/abs/1809.10341v2","title":"Deep Graph Infomax","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 Models","url":"/methods/category/graph-models","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":10,"papers_newest_first":[{"paper":null,"title":"Graph Pre-Training Models Are Strong Anomaly Detectors","date":"2024-10-24","arxiv_id":"2410.18487","n_code_links":0,"syntology":null},{"paper":"/paper/electioneering-the-network-dynamic-multi-step","title":"Dynamic Gradient Influencing for Viral Marketing Using Graph Neural Networks","date":"2024-03-19","arxiv_id":"2403.12399","n_code_links":1,"syntology":null},{"paper":null,"title":"On the Adversarial Robustness of Graph Contrastive Learning Methods","date":"2023-11-29","arxiv_id":"2311.17853","n_code_links":0,"syntology":null},{"paper":null,"title":"DGI: Easy and Efficient Inference for GNNs","date":"2022-11-28","arxiv_id":"2211.15082","n_code_links":0,"syntology":null},{"paper":"/paper/models-and-benchmarks-for-representation","title":"Models and Benchmarks for Representation Learning of Partially Observed Subgraphs","date":"2022-09-01","arxiv_id":"2209.00508","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-and-scaling-up-graph-contrastive","title":"Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination","date":"2022-06-03","arxiv_id":"2206.01535","n_code_links":1,"syntology":{"ran":4,"of":5,"unverified":1,"pointer_only":5}},{"paper":"/paper/contrastive-laplacian-eigenmaps-1","title":"Contrastive Laplacian Eigenmaps","date":"2022-01-14","arxiv_id":"2201.05493","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":"/paper/hdmi-high-order-deep-multiplex-infomax","title":"HDMI: High-order Deep Multiplex Infomax","date":"2021-02-15","arxiv_id":"2102.07810","n_code_links":1,"syntology":null},{"paper":"/paper/sce-scalable-network-embedding-from-sparsest","title":"SCE: Scalable Network Embedding from Sparsest Cut","date":"2020-06-30","arxiv_id":"2006.16499","n_code_links":1,"syntology":{"ran":3,"of":7,"unverified":4,"pointer_only":0}},{"paper":"/paper/deep-graph-infomax","title":"Deep Graph Infomax","date":"2018-09-27","arxiv_id":"1809.10341","n_code_links":11,"syntology":{"ran":24,"of":35,"unverified":11,"pointer_only":9}}],"papers_shown":10,"tasks":[{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":4},{"task":"/task/node-classification","name":"Node Classification","papers":3},{"task":"/task/representation-learning","name":"Representation Learning","papers":3},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/graph-anomaly-detection","name":"Graph Anomaly Detection","papers":1},{"task":"/task/graph-classification","name":"Graph Classification","papers":1},{"task":"/task/graph-embedding","name":"Graph Embedding","papers":1},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":1},{"task":"/task/inductive-learning","name":"Inductive Learning","papers":1},{"task":"/task/marketing","name":"Marketing","papers":1},{"task":"/task/network-embedding","name":"Network Embedding","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":1}],"tasks_shown":17,"n_tasks":17,"usage_by_year":[{"year":"2018","papers":1},{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":4},{"year":"2023","papers":1},{"year":"2024","papers":2}],"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/dgi"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}