{"id":"W4315630116","doi":"10.1109/globecom48099.2022.10000610","title":"Transfer Learning with Input Reconstruction Loss","year":2022,"lang":"en","type":"article","venue":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Transfer of learning; Artificial intelligence; Artificial neural network; Machine learning; Exploit; Wireless; Deep learning; Feature (linguistics); Task (project management); Wireless network; Distributed computing; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007861278,0.0003029388,0.0003146414,0.0001675662,0.002351061,0.0003791564,0.004085261,0.0000682985,0.001018441],"category_scores_gemma":[0.00005080223,0.0003365434,0.0001205376,0.002047803,0.0003027523,0.0009361405,0.00126281,0.00128543,0.0001094822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005006336,"about_ca_system_score_gemma":0.0005302413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002418118,"about_ca_topic_score_gemma":0.0002415509,"domain_scores_codex":[0.9963203,0.001226054,0.0005068075,0.0006766966,0.0007598533,0.0005102984],"domain_scores_gemma":[0.9969661,0.0001737667,0.0002019306,0.002213551,0.0002496336,0.000195049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001233548,0.0004334651,0.01064873,0.00002592392,0.0001818033,0.00004869757,0.002826026,0.02992322,0.0008986966,0.6580216,0.001711065,0.2951574],"study_design_scores_gemma":[0.0032591,0.001133596,0.00656954,0.00009063362,0.00009866376,0.001998628,0.009271445,0.4614047,0.0002036142,0.012057,0.5019454,0.001967751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07647331,0.001217991,0.8341156,0.01104962,0.001520069,0.0009212248,0.0001571541,0.001365202,0.07317984],"genre_scores_gemma":[0.9744316,0.0003211316,0.02313509,0.0007746458,0.00002685304,0.0002764247,0.00009956564,0.00001914425,0.0009154949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8979583,"threshold_uncertainty_score":0.9999087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03122715736480495,"score_gpt":0.2621237073563796,"score_spread":0.2308965499915747,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}