{"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/interventional-assays-for-the-latent-space-of","title":"Exploring the Latent Space of Autoencoders with Interventional Assays","arxiv_id":"2106.16091","date":"2021-06-30","proceeding":null,"authors":["Felix Leeb","Stefan Bauer","Michel Besserve","Bernhard Schölkopf"],"abstract":"Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the representation is usually uninterpretable, making analysis and principled progress challenging. We propose a framework, called latent responses, which exploits the locally contractive behavior exhibited by variational autoencoders to explore the learned manifold. More specifically, we develop tools to probe the representation using interventions in the latent space to quantify the relationships between latent variables. We extend the notion of disentanglement to take the learned generative process into account and consequently avoid the limitations of existing metrics that may rely on spurious correlations. Our analyses underscore the importance of studying the causal structure of the representation to improve performance on downstream tasks such as generation, interpolation, and inference of the factors of variation.","url_abs":"https://arxiv.org/abs/2106.16091v4","url_pdf":"https://arxiv.org/pdf/2106.16091v4.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":"interventional-assays-for-the-latent-space-of","repo_url":"https://github.com/felixludos/latent-responses","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.16091","atlas_url":"https://app.syntology.ai/?focus=2106.16091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.16091"}},"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":"deterministic:regex_extraction","url":"https://github.com/felixludos/latent-responses","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"ran":3,"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":"6714b05c725caffb","entry":"response_mat","repo":"felixludos/latent-responses","repo_kind":"official","path":"src/responses.py","file_url":"https://github.com/felixludos/latent-responses/blob/HEAD/src/responses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6714b05c725caffb"}},{"code_sha256_prefix":"070d219fb032a1fd","entry":"response_mat","repo":"felixludos/latent-responses","repo_kind":"official","path":"src/responses.py","file_url":"https://github.com/felixludos/latent-responses/blob/HEAD/src/responses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"070d219fb032a1fd"}},{"code_sha256_prefix":"8210347260100074","entry":"score_from_conditioned_response_mat","repo":"felixludos/latent-responses","repo_kind":"official","path":"src/responses.py","file_url":"https://github.com/felixludos/latent-responses/blob/HEAD/src/responses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8210347260100074"}},{"code_sha256_prefix":"39767c58bcd52855","entry":"Autoencoder","repo":"felixludos/latent-responses","repo_kind":"official","path":"src/responses.py","file_url":"https://github.com/felixludos/latent-responses/blob/HEAD/src/responses.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":"39767c58bcd52855"}},{"code_sha256_prefix":"70adfb01098fa961","entry":"conditioned_response_mat","repo":"felixludos/latent-responses","repo_kind":"official","path":"src/responses.py","file_url":"https://github.com/felixludos/latent-responses/blob/HEAD/src/responses.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":"70adfb01098fa961"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}