{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:56RRKZHIVBDIGWGINNCRNETJNY","short_pith_number":"pith:56RRKZHI","schema_version":"1.0","canonical_sha256":"efa31564e8a8468358c86b451692696e07cebd017c9d178277974372b4dc8647","source":{"kind":"arxiv","id":"2002.02913","version":4},"attestation_state":"computed","paper":{"title":"Learning Autoencoders with Relational Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dixin Luo, Hongteng Xu, Lawrence Carin, Ricardo Henao, Svati Shah","submitted_at":"2020-02-07T17:27:30Z","abstract_excerpt":"A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a \\emph{relational regularization} on the learnable latent prior. This regularization penalizes the fused Gromov-Wasserstein (FGW) distance between the latent prior and its corresponding posterior, allowing one to flexibly learn a structured prior distribution associated with the generative model. Moreover, it helps co-training of multiple autoencoders even if they have heterogeneous architectures and incomparable latent spaces. W"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2002.02913","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T17:27:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"af95a231ffaf8f34ec7bf13c0f1aaa37727d5fe60739ff283f4f22a8a9ca3006","abstract_canon_sha256":"058b4b717950d6ed048288f9d293ffdf9e4c8bb71330dbc61d5a5f03299ce180"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:43.276131Z","signature_b64":"VzkLnc1U/ggEJmXRHjRwWQQn6aa+UcRJjh33AV8quykzhTAclFWd3l1ZVtE8qPdMArrELjAuZkVWIoziHopKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efa31564e8a8468358c86b451692696e07cebd017c9d178277974372b4dc8647","last_reissued_at":"2026-07-05T01:13:43.275594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:43.275594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Autoencoders with Relational Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dixin Luo, Hongteng Xu, Lawrence Carin, Ricardo Henao, Svati Shah","submitted_at":"2020-02-07T17:27:30Z","abstract_excerpt":"A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a \\emph{relational regularization} on the learnable latent prior. This regularization penalizes the fused Gromov-Wasserstein (FGW) distance between the latent prior and its corresponding posterior, allowing one to flexibly learn a structured prior distribution associated with the generative model. Moreover, it helps co-training of multiple autoencoders even if they have heterogeneous architectures and incomparable latent spaces. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02913","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.02913/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.02913","created_at":"2026-07-05T01:13:43.275649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02913v4","created_at":"2026-07-05T01:13:43.275649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02913","created_at":"2026-07-05T01:13:43.275649+00:00"},{"alias_kind":"pith_short_12","alias_value":"56RRKZHIVBDI","created_at":"2026-07-05T01:13:43.275649+00:00"},{"alias_kind":"pith_short_16","alias_value":"56RRKZHIVBDIGWGI","created_at":"2026-07-05T01:13:43.275649+00:00"},{"alias_kind":"pith_short_8","alias_value":"56RRKZHI","created_at":"2026-07-05T01:13:43.275649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10089","citing_title":"Optimizing Latent Dimension Allocation in Hierarchical VAEs: Balancing Attenuation and Information Retention for OOD Detection","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY","json":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY.json","graph_json":"https://pith.science/api/pith-number/56RRKZHIVBDIGWGINNCRNETJNY/graph.json","events_json":"https://pith.science/api/pith-number/56RRKZHIVBDIGWGINNCRNETJNY/events.json","paper":"https://pith.science/paper/56RRKZHI"},"agent_actions":{"view_html":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY","download_json":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY.json","view_paper":"https://pith.science/paper/56RRKZHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02913&json=true","fetch_graph":"https://pith.science/api/pith-number/56RRKZHIVBDIGWGINNCRNETJNY/graph.json","fetch_events":"https://pith.science/api/pith-number/56RRKZHIVBDIGWGINNCRNETJNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY/action/storage_attestation","attest_author":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY/action/author_attestation","sign_citation":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY/action/citation_signature","submit_replication":"https://pith.science/pith/56RRKZHIVBDIGWGINNCRNETJNY/action/replication_record"}},"created_at":"2026-07-05T01:13:43.275649+00:00","updated_at":"2026-07-05T01:13:43.275649+00:00"}