{"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-guided-masked-autoencoders-for-domain","title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","arxiv_id":"2402.14789","date":"2024-02-22","proceeding":null,"authors":["Johnathan Xie","Yoonho Lee","Annie S. Chen","Chelsea Finn"],"abstract":"Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-trivial because the specifics of existing methods are tailored to each domain, such as domain-specific augmentations which reflect the invariances in the target task. While masked modeling is promising as a domain-agnostic framework for self-supervised learning because it does not rely on input augmentations, its mask sampling procedure remains domain-specific. We present Self-guided Masked Autoencoders (SMA), a fully domain-agnostic masked modeling method. SMA trains an attention based model using a masked modeling objective, by learning masks to sample without any domain-specific assumptions. We evaluate SMA on three self-supervised learning benchmarks in protein biology, chemical property prediction, and particle physics. We find SMA is capable of learning representations without domain-specific knowledge and achieves state-of-the-art performance on these three benchmarks.","url_abs":"https://arxiv.org/abs/2402.14789v1","url_pdf":"https://arxiv.org/pdf/2402.14789v1.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-guided-masked-autoencoders-for-domain","repo_url":"https://github.com/johnathan-xie/sma","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"slime-mould-algorithm-sma","method_name":"SMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"SMA","rank_in_archive_order":6,"of":20,"metrics":{"ROC-AUC":"84.3"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"SMA","rank_in_archive_order":13,"of":29,"metrics":{"ROC-AUC":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-esol","task":"Molecular Property Prediction","dataset":"ESOL","model":"SMA","rank_in_archive_order":11,"of":20,"metrics":{"RMSE":"0.623"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","task":"Molecular Property Prediction","dataset":"FreeSolv","model":"SMA","rank_in_archive_order":10,"of":22,"metrics":{"RMSE":"1.09"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"SMA","rank_in_archive_order":5,"of":11,"metrics":{"AUC":"0.789"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on","task":"Molecular Property Prediction","dataset":"Lipophilicity","model":"SMA","rank_in_archive_order":2,"of":13,"metrics":{"RMSE":"0.609"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.14789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14789"}},"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/johnathan-xie/sma","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_fixture":1,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":15,"ran":8,"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":"a727df5fd2f5599a","entry":"check_number_comma","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/convert_slow_tokenizer.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/convert_slow_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a727df5fd2f5599a"}},{"code_sha256_prefix":"1e4b7ef652519a56","entry":"cosine_scheduler","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/models/sma/modeling_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/modeling_sma.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e4b7ef652519a56"}},{"code_sha256_prefix":"400c88e8ff1249dd","entry":"create_vocab","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/models/sma/tokenization_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/tokenization_sma.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"400c88e8ff1249dd"}},{"code_sha256_prefix":"e3aa4e8e74369506","entry":"drop_path","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/models/sma/modeling_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/modeling_sma.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e3aa4e8e74369506"}},{"code_sha256_prefix":"b220e701be05a184","entry":"ensure_valid_input","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/convert_graph_to_onnx.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/convert_graph_to_onnx.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b220e701be05a184"}},{"code_sha256_prefix":"7efe3db5c9e2f94d","entry":"generate_identified_filename","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/convert_graph_to_onnx.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/convert_graph_to_onnx.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7efe3db5c9e2f94d"}},{"code_sha256_prefix":"6e02aa508f18b20f","entry":"invert_attention_mask","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/models/sma/modeling_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/modeling_sma.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e02aa508f18b20f"}},{"code_sha256_prefix":"e7fbc7a74a3457c7","entry":"load_vocab","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/models/sma/tokenization_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/tokenization_sma.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7fbc7a74a3457c7"}},{"code_sha256_prefix":"9d93436a1b858d0e","entry":"convert_slow_tokenizer","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/convert_slow_tokenizer.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/convert_slow_tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d93436a1b858d0e"}},{"code_sha256_prefix":"9dbff79b658755c9","entry":"create_transforms","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/models/sma/transforms_sma.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/models/sma/transforms_sma.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9dbff79b658755c9"}},{"code_sha256_prefix":"37a5eed2dbd663ca","entry":"gelu_fast","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/activations_tf.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/activations_tf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37a5eed2dbd663ca"}},{"code_sha256_prefix":"dd3166a87bc972ff","entry":"get_configuration_file","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/configuration_utils.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/configuration_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd3166a87bc972ff"}},{"code_sha256_prefix":"0da835817b8a57bc","entry":"infer_shapes","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/convert_graph_to_onnx.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/convert_graph_to_onnx.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0da835817b8a57bc"}},{"code_sha256_prefix":"cc8c8c3ebf0c343f","entry":"mish","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/activations_tf.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/activations_tf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc8c8c3ebf0c343f"}},{"code_sha256_prefix":"e2d56cb91f999bef","entry":"quick_gelu","repo":"johnathan-xie/sma","repo_kind":"official","path":"src/transformers/activations_tf.py","file_url":"https://github.com/johnathan-xie/sma/blob/HEAD/src/transformers/activations_tf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e2d56cb91f999bef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}