{"doi":"10.1109/tnnls.2021.3082316","title":"What and Where: Learn to Plug Adapters via NAS for Multidomain Learning","abstract":null,"journal":"IEEE Transactions on Neural Networks and Learning Systems","year":2022,"id":641672,"datarank":0.4566783656585135,"base_score":3.044522437723423,"endowment":3.044522437723423,"self_citation_contribution":0.4566783656585135,"citation_network_contribution":0.0,"self_endowment_contribution":0.4566783656585135,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":20,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":53195,"name":"Hao Zeng","orcid":"0000-0003-4688-1563","position":1,"is_corresponding":false},{"id":39902,"name":"Xin Qin","orcid":null,"position":2,"is_corresponding":false},{"id":1668540,"name":"Yongjian Fu","orcid":"0000-0003-1650-7167","position":3,"is_corresponding":false},{"id":1311861,"name":"Hui Wang","orcid":"0000-0003-4970-5282","position":4,"is_corresponding":false},{"id":1668541,"name":"Bourahla Omar","orcid":null,"position":5,"is_corresponding":false},{"id":1299612,"name":"Xi Li","orcid":"0009-0008-4480-8251","position":6,"is_corresponding":false},{"id":1668539,"name":"Hanbin Zhao","orcid":"0000-0001-8906-4534","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"What and Where: Learn to Plug Adapters via NAS for Multidomain Learning","abstract":"As an important and challenging problem, multidomain learning (MDL) typically seeks a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with neural architecture search (NAS), which automatically determines where to plug for those adapter modules. Furthermore, we propose an NAS-adapter module for adapter structure design in an NAS-driven learning scheme, which automatically discovers effective adapter module structures for different domains. Experimental results demonstrate the effectiveness of our MDL model against existing approaches under the conditions of comparable performance.","is_dataset_classified":null,"base_score":3.044522437723423,"endowment":3.044522437723423,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"34310322","pmcid":null,"openalex_id":"https://openalex.org/W3184035966","authors":[],"funders":[{"funder_name":"National Key Research and Development Program of China","grant_id":"2020AAA0107400","title":null},{"funder_name":"National Natural Science Foundation of China","grant_id":"U20A20222","title":null},{"funder_name":"Zhejiang Provincial Natural Science Foundation of China","grant_id":"LR19F020004","title":null},{"funder_name":"Key Scientific Technological Innovation Research Project by Ministry of Education","grant_id":"","title":null}],"total_grants":4,"fwci":1.6378,"citation_percentile":0.86402521,"influential_citations":0,"citation_trend":[{"year":2020,"count":1},{"year":2021,"count":4},{"year":2022,"count":3},{"year":2023,"count":2},{"year":2024,"count":3},{"year":2025,"count":6},{"year":2026,"count":1}],"oa_status":"closed","license":"https://doi.org/10.15223/policy-029","oa_locations":[{"url":"http://xplorestaging.ieee.org/ielx7/5962385/9931397/09494038.pdf?arnumber=9494038","host_type":"publisher"},{"url":"https://doi.org/10.1109/tnnls.2021.3082316","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/34310322","host_type":"repository"}],"fields_of_study":["Domain Adaptation and Few-Shot Learning","Multimodal Machine Learning Applications","Advanced Neural Network Applications","Neural Networks, Computer","Software","Learning","Plant Extracts"],"mesh_terms":["Learning","Plant Extracts","Software","Neural Networks, Computer"],"keywords":["Adapter (computing)","Computer science","Architecture","Artificial intelligence","Operating system"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-07T19:39:13.507139Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}