{"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/online-continual-learning-with-maximally","title":"Online Continual Learning with Maximally Interfered Retrieval","arxiv_id":"1908.04742","date":"2019-08-11","proceeding":null,"authors":["Rahaf Aljundi","Lucas Caccia","Eugene Belilovsky","Massimo Caccia","Min Lin","Laurent Charlin","Tinne Tuytelaars"],"abstract":"Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or \"single-pass through the data\" setting has gained attention recently as a natural setting that is difficult to tackle. Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks. These approaches typically rely on randomly selecting samples from the replay memory or from a generative model, which is suboptimal. In this work, we consider a controlled sampling of memories for replay. We retrieve the samples which are most interfered, i.e. whose prediction will be most negatively impacted by the foreseen parameters update. We show a formulation for this sampling criterion in both the generative replay and the experience replay setting, producing consistent gains in performance and greatly reduced forgetting. We release an implementation of our method at https://github.com/optimass/Maximally_Interfered_Retrieval.","url_abs":"https://arxiv.org/abs/1908.04742v3","url_pdf":"https://arxiv.org/pdf/1908.04742v3.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":"online-continual-learning-with-maximally","repo_url":"https://github.com/optimass/Maximally_Interfered_Retrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.04742","atlas_url":"https://app.syntology.ai/?focus=1908.04742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04742"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/optimass/Maximally_Interfered_Retrieval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":12},"by_repo_kind":{"official":{"samples":13,"ran":1,"repositories":1}},"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":"ec20f22a185cd708","entry":"conv3x3","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"model.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec20f22a185cd708"}},{"code_sha256_prefix":"c6b1a6798ffeb442","entry":"ResNet18","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"model.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6b1a6798ffeb442"}},{"code_sha256_prefix":"7f8a097320e69838","entry":"get_cifar_buffer","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"buffer.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/buffer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f8a097320e69838"}},{"code_sha256_prefix":"a1dbf374743f5c7b","entry":"get_future_step_parameters","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"utils.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1dbf374743f5c7b"}},{"code_sha256_prefix":"947e501e9d13e0ce","entry":"get_grad_vector","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"utils.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"947e501e9d13e0ce"}},{"code_sha256_prefix":"93eb2ca19dee45bc","entry":"get_permuted_mnist","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"data.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93eb2ca19dee45bc"}},{"code_sha256_prefix":"de5833eda07e76b8","entry":"get_split_cifar10","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"data.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de5833eda07e76b8"}},{"code_sha256_prefix":"a78b3966b0df22e0","entry":"get_split_mnist","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"data.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a78b3966b0df22e0"}},{"code_sha256_prefix":"7d71e086676bc142","entry":"log_normal_diag","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"VAE/distributions.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/VAE/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d71e086676bc142"}},{"code_sha256_prefix":"a811f7f779566e3e","entry":"log_normal_normalized","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"VAE/distributions.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/VAE/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a811f7f779566e3e"}},{"code_sha256_prefix":"a39500bc34bfcdd6","entry":"log_normal_standard","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"VAE/distributions.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/VAE/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a39500bc34bfcdd6"}},{"code_sha256_prefix":"651082fb231f9a1d","entry":"onehot","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"utils.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"651082fb231f9a1d"}},{"code_sha256_prefix":"952eca59dbb44579","entry":"retrieve_hybrid","repo":"optimass/Maximally_Interfered_Retrieval","repo_kind":"official","path":"mir.py","file_url":"https://github.com/optimass/Maximally_Interfered_Retrieval/blob/HEAD/mir.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"952eca59dbb44579"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}