{"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/self-assttentive-associative-memory","title":"Self-Attentive Associative Memory","arxiv_id":"2002.03519","date":"2020-02-10","proceeding":"ICML 2020 1","authors":["Hung Le","Truyen Tran","Svetha Venkatesh"],"abstract":"Heretofore, neural networks with external memory are restricted to single memory with lossy representations of memory interactions. A rich representation of relationships between memory pieces urges a high-order and segregated relational memory. In this paper, we propose to separate the storage of individual experiences (item memory) and their occurring relationships (relational memory). The idea is implemented through a novel Self-attentive Associative Memory (SAM) operator. Found upon outer product, SAM forms a set of associative memories that represent the hypothetical high-order relationships between arbitrary pairs of memory elements, through which a relational memory is constructed from an item memory. The two memories are wired into a single sequential model capable of both memorization and relational reasoning. We achieve competitive results with our proposed two-memory model in a diversity of machine learning tasks, from challenging synthetic problems to practical testbeds such as geometry, graph, reinforcement learning, and question answering.","url_abs":"https://arxiv.org/abs/2002.03519v3","url_pdf":"https://arxiv.org/pdf/2002.03519v3.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":"self-assttentive-associative-memory","repo_url":"https://github.com/thaihungle/SAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-babi","task":"Question Answering","dataset":"bAbi","model":"STM","rank_in_archive_order":1,"of":14,"metrics":{"Accuracy (trained on 10k)":"99.85%","Mean Error Rate":"0.39%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.03519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03519"}},"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/thaihungle/SAM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":"21a7f97ee3e0b7cc","entry":"norm_col_init","repo":"thaihungle/SAM","repo_kind":"official","path":"baselines/sam/utils.py","file_url":"https://github.com/thaihungle/SAM/blob/HEAD/baselines/sam/utils.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21a7f97ee3e0b7cc"}},{"code_sha256_prefix":"b489920b54ff3e28","entry":"op_att","repo":"thaihungle/SAM","repo_kind":"official","path":"baselines/sam/stm_basic.py","file_url":"https://github.com/thaihungle/SAM/blob/HEAD/baselines/sam/stm_basic.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":"b489920b54ff3e28"}},{"code_sha256_prefix":"4000c95fa330f2ce","entry":"read_config","repo":"thaihungle/SAM","repo_kind":"official","path":"baselines/sam/utils.py","file_url":"https://github.com/thaihungle/SAM/blob/HEAD/baselines/sam/utils.py","link_basis":"harvester_set","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":"4000c95fa330f2ce"}},{"code_sha256_prefix":"69a12f5cd80a0f87","entry":"sdp_att","repo":"thaihungle/SAM","repo_kind":"official","path":"baselines/sam/stm_basic.py","file_url":"https://github.com/thaihungle/SAM/blob/HEAD/baselines/sam/stm_basic.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":"69a12f5cd80a0f87"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}