{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/continual-learning-with-tiny-episodic","title":"On Tiny Episodic Memories in Continual Learning","arxiv_id":"1902.10486","date":"2019-02-27","proceeding":null,"authors":["Arslan Chaudhry","Marcus Rohrbach","Mohamed Elhoseiny","Thalaiyasingam Ajanthan","Puneet K. Dokania","Philip H. S. Torr","Marc'Aurelio Ranzato"],"abstract":"In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform previous tasks. One way to endow the learner the ability to perform tasks seen in the past is to store a small memory, dubbed episodic memory, that stores few examples from previous tasks and then to replay these examples when training for future tasks. In this work, we empirically analyze the effectiveness of a very small episodic memory in a CL setup where each training example is only seen once. Surprisingly, across four rather different supervised learning benchmarks adapted to CL, a very simple baseline, that jointly trains on both examples from the current task as well as examples stored in the episodic memory, significantly outperforms specifically designed CL approaches with and without episodic memory. Interestingly, we find that repetitive training on even tiny memories of past tasks does not harm generalization, on the contrary, it improves it, with gains between 7\\% and 17\\% when the memory is populated with a single example per class.","url_abs":"https://arxiv.org/abs/1902.10486v4","url_pdf":"https://arxiv.org/pdf/1902.10486v4.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":"continual-learning-with-tiny-episodic","repo_url":"https://github.com/facebookresearch/agem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"continual-learning-with-tiny-episodic","repo_url":"https://github.com/chandar-lab/CMAL_Hanabi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"continual-learning-with-tiny-episodic","repo_url":"https://github.com/chandar-lab/Lifelong-Hanabi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"continual-learning-with-tiny-episodic","repo_url":"https://github.com/firehose-dataset/congrad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continual-learning-with-tiny-episodic","repo_url":"https://github.com/yaqianzhang/repeatedaugmentedrehearsal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"continual-learning-with-tiny-episodic","repo_url":"https://github.com/ContinualAI/avalanche","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/class-incremental-learning-on-cifar100","task":"Class Incremental Learning","dataset":"cifar100","model":"EMR","rank_in_archive_order":6,"of":7,"metrics":{"10-stage average accuracy":"48.66"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.10486","atlas_url":"https://app.syntology.ai/?focus=1902.10486","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1902.10486"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.10486\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.10486"},"call":"get_concepts_for_paper(arxiv_id=\"1902.10486\")"}],"by_repo":[{"repo":"facebookresearch/agem","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.00420"],"harvested_for_calls":[{"arxiv_id":"1812.00420","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.00420"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.00420\")"}]},{"repo":"chandar-lab/CMAL_Hanabi","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"chandar-lab/Lifelong-Hanabi","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"firehose-dataset/congrad","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yaqianzhang/repeatedaugmentedrehearsal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ContinualAI/avalanche","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1606.09282","2007.13904"],"harvested_for_calls":[{"arxiv_id":"1606.09282","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.09282"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.09282\")"},{"arxiv_id":"2007.13904","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.13904"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.13904\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ca9bbacedd50620037bc877121d4802b8ca5a453d7dd3f4058b5d8d66db5d9ab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}