{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lifelong-graph-learning","title":"Lifelong Graph Learning","arxiv_id":"2009.00647","date":"2020-09-01","proceeding":"CVPR 2022 1","authors":["Chen Wang","Yuheng Qiu","Dasong Gao","Sebastian Scherer"],"abstract":"Graph neural networks (GNN) are powerful models for many graph-structured tasks. Existing models often assume that the complete structure of the graph is available during training. In practice, however, graph-structured data is usually formed in a streaming fashion so that learning a graph continuously is often necessary. In this paper, we bridge GNN and lifelong learning by converting a continual graph learning problem to a regular graph learning problem so GNN can inherit the lifelong learning techniques developed for convolutional neural networks (CNN). We propose a new topology, the feature graph, which takes features as new nodes and turns nodes into independent graphs. This successfully converts the original problem of node classification to graph classification. In the experiments, we demonstrate the efficiency and effectiveness of feature graph networks (FGN) by continuously learning a sequence of classical graph datasets. We also show that FGN achieves superior performance in two applications, i.e., lifelong human action recognition with wearable devices and feature matching. To the best of our knowledge, FGN is the first method to bridge graph learning and lifelong learning via a novel graph topology. Source code is available at https://github.com/wang-chen/LGL","url_abs":"https://arxiv.org/abs/2009.00647v4","url_pdf":"https://arxiv.org/pdf/2009.00647v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lifelong-graph-learning","repo_url":"https://github.com/wang-chen/LGL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lifelong-graph-learning","repo_url":"https://github.com/wang-chen/lgl-action-recognition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lifelong-graph-learning","repo_url":"https://github.com/MindSpore-scientific-2/code-12/tree/main/LGL-INR-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.00647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.00647"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-12/tree/main/LGL-INR-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wang-chen/lgl-action-recognition","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wang-chen/LGL","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"wang-chen/lgl-action-recognition","repo_kind":"official","path":"torch_util/tools.py","file_url":"https://github.com/wang-chen/lgl-action-recognition/blob/HEAD/torch_util/tools.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"2367201daa1ad118","entry":"performance","repo":"wang-chen/lgl-action-recognition","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/wang-chen/lgl-action-recognition/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2367201daa1ad118"}},{"code_sha256_prefix":"daa75a513d29dd11","entry":"sum_aggregation","repo":"wang-chen/LGL","repo_kind":"official","path":"models/GCN.py","file_url":"https://github.com/wang-chen/LGL/blob/HEAD/models/GCN.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"daa75a513d29dd11"}},{"code_sha256_prefix":"d76980f73de94b11","entry":"train","repo":"wang-chen/lgl-action-recognition","repo_kind":"official","path":"regular.py","file_url":"https://github.com/wang-chen/lgl-action-recognition/blob/HEAD/regular.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d76980f73de94b11"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}