{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/palt-parameter-lite-transfer-of-language","title":"PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion","arxiv_id":"2210.13715","date":"2022-10-25","proceeding":null,"authors":["Jianhao Shen","Chenguang Wang","Ye Yuan","Jiawei Han","Heng Ji","Koushik Sen","Ming Zhang","Dawn Song"],"abstract":"This paper presents a parameter-lite transfer learning approach of pretrained language models (LM) for knowledge graph (KG) completion. Instead of finetuning, which modifies all LM parameters, we only tune a few new parameters while keeping the original LM parameters fixed. We establish this via reformulating KG completion as a \"fill-in-the-blank\" task, and introducing a parameter-lite encoder on top of the original LMs. We show that, by tuning far fewer parameters than finetuning, LMs transfer non-trivially to most tasks and reach competitiveness with prior state-of-the-art approaches. For instance, we outperform the fully finetuning approaches on a KG completion benchmark by tuning only 1% of the parameters. The code and datasets are available at \\url{https://github.com/yuanyehome/PALT}.","url_abs":"https://arxiv.org/abs/2210.13715v1","url_pdf":"https://arxiv.org/pdf/2210.13715v1.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":"palt-parameter-lite-transfer-of-language","repo_url":"https://github.com/yuanyehome/palt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"PALT","rank_in_archive_order":69,"of":75,"metrics":{"Hits@10":"0.444","MR":"144"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-umls","task":"Link Prediction","dataset":"UMLS","model":"PALT","rank_in_archive_order":7,"of":10,"metrics":{"Hits@10":"0.990","MR":"1.57"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"PALT","rank_in_archive_order":10,"of":75,"metrics":{"Hits@10":"0.693","MR":"61"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.13715","atlas_url":"https://app.syntology.ai/?focus=2210.13715","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2210.13715"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.13715\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.13715"},"call":"get_concepts_for_paper(arxiv_id=\"2210.13715\")"}],"by_repo":[{"repo":"yuanyehome/palt","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"80edba64672c9f9949d19de52832c3e9752caf0b207cf9a43f4002b3442c80a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}