{"id":18001813,"url":"https://github.com/josephkj/merlin","last_synced_at":"2025-03-26T08:31:00.795Z","repository":{"id":81824029,"uuid":"271187817","full_name":"JosephKJ/merlin","owner":"JosephKJ","description":"(NeurIPS 2020) Meta-Consolidation for Continual Learning","archived":false,"fork":false,"pushed_at":"2021-03-04T09:41:08.000Z","size":11388,"stargazers_count":37,"open_issues_count":2,"forks_count":7,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-21T11:50:37.852Z","etag":null,"topics":["continual-learning","incremental-learning","meta-learning","neurips","neurips-2020"],"latest_commit_sha":null,"homepage":"https://josephkj.in/projects/MERLIN/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JosephKJ.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-06-10T05:33:38.000Z","updated_at":"2025-03-10T03:29:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"36eacded-21e7-4ca9-b2f1-3254e3b8bf9d","html_url":"https://github.com/JosephKJ/merlin","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosephKJ%2Fmerlin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosephKJ%2Fmerlin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosephKJ%2Fmerlin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosephKJ%2Fmerlin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JosephKJ","download_url":"https://codeload.github.com/JosephKJ/merlin/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245618613,"owners_count":20645030,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["continual-learning","incremental-learning","meta-learning","neurips","neurips-2020"],"created_at":"2024-10-29T23:18:52.531Z","updated_at":"2025-03-26T08:31:00.788Z","avatar_url":"https://github.com/JosephKJ.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Meta-Consolidation for Continual Learning \n### To appear at NeurIPS 2020\n\n### arXiv link: https://arxiv.org/abs/2010.00352\n\nThe ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning.\nWe assume that weights of a neural network, for solving task, come from a meta-distribution. This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once.\nOur experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.\n\nWe herein share the code to replicate experiments with Split MNIST dataset.\n\n#### Usage\n\n```python\npython main.py\n```\n\n#### Requirements\n\n```shell script\nPython: 3.7.4\nPyTorch: 1.4.0\nTorchVision: 0.5.0\nCUDA Version: 10.1 \n```\n\n#### Citation\n\n``` \n@inproceedings{NEURIPS2020_a5585a4d,\n author = {K J, Joseph and N Balasubramanian, Vineeth},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {H. Larochelle and M. Ranzato and R. Hadsell and M. F. Balcan and H. Lin},\n pages = {14374--14386},\n publisher = {Curran Associates, Inc.},\n title = {Meta-Consolidation for Continual Learning},\n url = {https://proceedings.neurips.cc/paper/2020/file/a5585a4d4b12277fee5cad0880611bc6-Paper.pdf},\n volume = {33},\n year = {2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosephkj%2Fmerlin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjosephkj%2Fmerlin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosephkj%2Fmerlin/lists"}