{"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/unsupervised-disentangled-representation","title":"Unsupervised Disentangled Representation Learning with Analogical Relations","arxiv_id":"1804.09502","date":"2018-04-25","proceeding":null,"authors":["Zejian Li","Yongchuan Tang","Yongxing He"],"abstract":"Learning the disentangled representation of interpretable generative factors\nof data is one of the foundations to allow artificial intelligence to think\nlike people. In this paper, we propose the analogical training strategy for the\nunsupervised disentangled representation learning in generative models. The\nanalogy is one of the typical cognitive processes, and our proposed strategy is\nbased on the observation that sample pairs in which one is different from the\nother in one specific generative factor show the same analogical relation.\nThus, the generator is trained to generate sample pairs from which a designed\nclassifier can identify the underlying analogical relation. In addition, we\npropose a disentanglement metric called the subspace score, which is inspired\nby subspace learning methods and does not require supervised information.\nExperiments show that our proposed training strategy allows the generative\nmodels to find the disentangled factors, and that our methods can give\ncompetitive performances as compared with the state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1804.09502v1","url_pdf":"http://arxiv.org/pdf/1804.09502v1.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":"unsupervised-disentangled-representation","repo_url":"https://github.com/ZejianLi/analogical-training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09502"}},"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/ZejianLi/analogical-training","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"fdef71810898429e","entry":"cov","repo":"ZejianLi/analogical-training","repo_kind":"official","path":"utils_torch.py","file_url":"https://github.com/ZejianLi/analogical-training/blob/HEAD/utils_torch.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":"fdef71810898429e"}},{"code_sha256_prefix":"c956375b18b5df1b","entry":"load_dataset","repo":"ZejianLi/analogical-training","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ZejianLi/analogical-training/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":"c956375b18b5df1b"}},{"code_sha256_prefix":"9240e6153e775d77","entry":"load_dataset_MNIST","repo":"ZejianLi/analogical-training","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ZejianLi/analogical-training/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":"9240e6153e775d77"}},{"code_sha256_prefix":"3affaff4227d7155","entry":"load_dataset_MNIST_small","repo":"ZejianLi/analogical-training","repo_kind":"official","path":"utils.py","file_url":"https://github.com/ZejianLi/analogical-training/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":"3affaff4227d7155"}},{"code_sha256_prefix":"f956a95ded1db27c","entry":"to_np","repo":"ZejianLi/analogical-training","repo_kind":"official","path":"utils_torch.py","file_url":"https://github.com/ZejianLi/analogical-training/blob/HEAD/utils_torch.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":"f956a95ded1db27c"}},{"code_sha256_prefix":"e9c28bf41d933d2b","entry":"to_var","repo":"ZejianLi/analogical-training","repo_kind":"official","path":"utils_torch.py","file_url":"https://github.com/ZejianLi/analogical-training/blob/HEAD/utils_torch.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":"e9c28bf41d933d2b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}