{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6K6LSDSYME6B7AEYXXSTICSAS4","short_pith_number":"pith:6K6LSDSY","schema_version":"1.0","canonical_sha256":"f2bcb90e58613c1f8098bde5340a409720a72918a280c3f6d2fc1cce0b5e343b","source":{"kind":"arxiv","id":"1911.05034","version":2},"attestation_state":"computed","paper":{"title":"Learning Sparse Sharing Architectures for Multiple Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hang Yan, Pengfei Liu, Tianxiang Sun, Xiaonan Li, Xipeng Qiu, Xuanjing Huang, Yunfan Shao","submitted_at":"2019-11-12T17:50:35Z","abstract_excerpt":"Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing. How choosing a suitable sharing mechanism depends on the relations among the tasks, which is not easy since it is difficult to understand the underlying shared factors among these tasks. In this paper, we propose a novel parameter sharing mechanism, named \\emph{Sparse Sharing}. Given multiple tasks, our approach automatically finds a sparse sharing structure. We start with an over-parameterized base network, from which each task extracts a subnetwork. The "},"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":"1911.05034","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-12T17:50:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e4198e2104a7bde1d189c58f58cc498c11ca91fd81ccc3af1ee5d3ee02889c4f","abstract_canon_sha256":"ff997b5b64fadf26934c132f308ff2dc8d28245b44da484f36e3cc490925f7e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:39.019874Z","signature_b64":"lFKOS56Qzq6BTkrV+71DpRORH8Vlmj4UJjgahVa/zgpymVCf5d4QAGPa74RShlFTFSTx+TEAtD8ePrAbjrCzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2bcb90e58613c1f8098bde5340a409720a72918a280c3f6d2fc1cce0b5e343b","last_reissued_at":"2026-07-05T00:19:39.019481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:39.019481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Sparse Sharing Architectures for Multiple Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hang Yan, Pengfei Liu, Tianxiang Sun, Xiaonan Li, Xipeng Qiu, Xuanjing Huang, Yunfan Shao","submitted_at":"2019-11-12T17:50:35Z","abstract_excerpt":"Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing. How choosing a suitable sharing mechanism depends on the relations among the tasks, which is not easy since it is difficult to understand the underlying shared factors among these tasks. In this paper, we propose a novel parameter sharing mechanism, named \\emph{Sparse Sharing}. Given multiple tasks, our approach automatically finds a sparse sharing structure. We start with an over-parameterized base network, from which each task extracts a subnetwork. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05034","kind":"arxiv","version":2},"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/1911.05034/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":"1911.05034","created_at":"2026-07-05T00:19:39.019539+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05034v2","created_at":"2026-07-05T00:19:39.019539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05034","created_at":"2026-07-05T00:19:39.019539+00:00"},{"alias_kind":"pith_short_12","alias_value":"6K6LSDSYME6B","created_at":"2026-07-05T00:19:39.019539+00:00"},{"alias_kind":"pith_short_16","alias_value":"6K6LSDSYME6B7AEY","created_at":"2026-07-05T00:19:39.019539+00:00"},{"alias_kind":"pith_short_8","alias_value":"6K6LSDSY","created_at":"2026-07-05T00:19:39.019539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4","json":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4.json","graph_json":"https://pith.science/api/pith-number/6K6LSDSYME6B7AEYXXSTICSAS4/graph.json","events_json":"https://pith.science/api/pith-number/6K6LSDSYME6B7AEYXXSTICSAS4/events.json","paper":"https://pith.science/paper/6K6LSDSY"},"agent_actions":{"view_html":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4","download_json":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4.json","view_paper":"https://pith.science/paper/6K6LSDSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05034&json=true","fetch_graph":"https://pith.science/api/pith-number/6K6LSDSYME6B7AEYXXSTICSAS4/graph.json","fetch_events":"https://pith.science/api/pith-number/6K6LSDSYME6B7AEYXXSTICSAS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4/action/storage_attestation","attest_author":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4/action/author_attestation","sign_citation":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4/action/citation_signature","submit_replication":"https://pith.science/pith/6K6LSDSYME6B7AEYXXSTICSAS4/action/replication_record"}},"created_at":"2026-07-05T00:19:39.019539+00:00","updated_at":"2026-07-05T00:19:39.019539+00:00"}