{"url":"/method/tgn","slug":"tgn","name":"TGN","full_name":"Temporal Graph Network","full_name_withheld":false,"description_markdown":"**Temporal Graph Network**, or **TGN**, is a framework for deep learning on dynamic graphs represented as sequences of timed events. The memory (state) of the model at time $t$ consists of a vector $\\mathbf{s}_i(t)$ for each node $i$ the model has seen so far. The memory of a node is updated after an event (e.g. interaction with another node or node-wise change), and its purpose is to represent the node's history in a compressed format. Thanks to this specific module, TGNs have the capability to memorize long term dependencies for each node in the graph. When a new node is encountered, its memory is initialized as the zero vector, and it is then updated for each event involving the node, even after the model has finished training.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","paper":"/paper/temporal-graph-networks-for-deep-learning-on","first_author":"Emanuele Rossi","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/temporal-graph-networks-for-deep-learning-on"},"source":{"url":"https://arxiv.org/abs/2006.10637v3","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","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":16,"archive_num_papers":16,"papers_newest_first":[{"paper":null,"title":"A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams","date":"2025-06-24","arxiv_id":"2506.19282","n_code_links":0,"syntology":null},{"paper":"/paper/trajectory-encoding-temporal-graph-networks","title":"Trajectory Encoding Temporal Graph Networks","date":"2025-04-15","arxiv_id":"2504.11386","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-the-expressivity-of-temporal-graph","title":"Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification","date":"2024-11-06","arxiv_id":"2411.03596","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":"/paper/retrofitting-temporal-graph-neural-networks","title":"Retrofitting Temporal Graph Neural Networks with Transformer","date":"2024-09-09","arxiv_id":"2409.05477","n_code_links":1,"syntology":null},{"paper":null,"title":"UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphs","date":"2024-07-17","arxiv_id":"2407.12269","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-graph-rewiring-with-expander-graphs","title":"Temporal Graph Rewiring with Expander Graphs","date":"2024-06-04","arxiv_id":"2406.02362","n_code_links":1,"syntology":null},{"paper":null,"title":"Temporal Graph Networks for Graph Anomaly Detection in Financial Networks","date":"2024-03-27","arxiv_id":"2404.00060","n_code_links":0,"syntology":null},{"paper":"/paper/a-temporal-graph-network-framework-for","title":"A Temporal Graph Network Framework for Dynamic Recommendation","date":"2024-03-24","arxiv_id":"2403.16066","n_code_links":1,"syntology":null},{"paper":null,"title":"HOT: Higher-Order Dynamic Graph Representation Learning with Efficient Transformers","date":"2023-11-30","arxiv_id":"2311.18526","n_code_links":0,"syntology":null},{"paper":"/paper/towards-temporal-edge-regression-a-case-study","title":"Towards Temporal Edge Regression: A Case Study on Agriculture Trade Between Nations","date":"2023-08-15","arxiv_id":"2308.07883","n_code_links":1,"syntology":null},{"paper":null,"title":"Analysis of different temporal graph neural network configurations on dynamic graphs","date":"2023-05-02","arxiv_id":"2305.01128","n_code_links":0,"syntology":null},{"paper":"/paper/dyg2vec-representation-learning-for-dynamic","title":"DyG2Vec: Efficient Representation Learning for Dynamic Graphs","date":"2022-10-30","arxiv_id":"2210.16906","n_code_links":2,"syntology":null},{"paper":"/paper/rethinking-the-memory-staleness-problem-in","title":"Rethinking The Memory Staleness Problem In Dynamics GNN","date":"2022-09-06","arxiv_id":"2209.02462","n_code_links":1,"syntology":null},{"paper":null,"title":"Adaptive Data Augmentation on Temporal Graphs","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Multi Scale Temporal Graph Networks For Skeleton-based Action Recognition","date":"2020-12-05","arxiv_id":"2012.02970","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-graph-networks-for-deep-learning-on","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","date":"2020-06-18","arxiv_id":"2006.10637","n_code_links":10,"syntology":{"ran":4,"of":19,"unverified":15,"pointer_only":0}}],"papers_shown":16,"tasks":[{"task":"/task/link-prediction","name":"Link Prediction","papers":6},{"task":"/task/node-classification","name":"Node Classification","papers":4},{"task":"/task/dynamic-link-prediction","name":"Dynamic Link Prediction","papers":2},{"task":"/task/dynamic-node-classification","name":"Dynamic Node Classification","papers":2},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":2},{"task":"/task/prediction","name":"Prediction","papers":2},{"task":"/task/recommendation-systems","name":"Recommendation Systems","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2},{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":1},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/fraud-detection","name":"Fraud Detection","papers":1},{"task":"/task/graph-anomaly-detection","name":"Graph Anomaly Detection","papers":1},{"task":"/task/graph-attention","name":"Graph Attention","papers":1},{"task":"/task/graph-embedding","name":"Graph Embedding","papers":1},{"task":"/task/graph-learning","name":"Graph Learning","papers":1},{"task":"/task/graph-regression","name":"Graph Regression","papers":1},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":1},{"task":"/task/graph-sampling","name":"Graph Sampling","papers":1}],"tasks_shown":20,"n_tasks":27,"usage_by_year":[{"year":"2020","papers":2},{"year":"2021","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":3},{"year":"2024","papers":6},{"year":"2025","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/tgn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}