{"id":"W4403517697","doi":"10.3233/faia240816","title":"Mask-Encoded Sparsification: Mitigating Biased Gradients in Communication-Efficient Split Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Jiangsu Province; Government of Jiangsu Province; Canadian Institute for Advanced Research; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006260619,0.0003082424,0.0003559688,0.000629353,0.0003004389,0.0002935319,0.0009416511,0.0002331941,0.00002200081],"category_scores_gemma":[0.00004565572,0.0003452754,0.00008242324,0.0004891265,0.000222066,0.0001154408,0.0002850715,0.0009473738,0.0002021596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001504751,"about_ca_system_score_gemma":0.00007516761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001021205,"about_ca_topic_score_gemma":0.00009913003,"domain_scores_codex":[0.9977088,0.0000592903,0.0007968069,0.0008312427,0.0002715938,0.0003322538],"domain_scores_gemma":[0.9986155,0.0001402927,0.0002531784,0.0008137112,0.00006862659,0.0001086771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003371214,0.00005608151,0.0002442484,0.00004310676,0.00001309478,0.000004334012,0.001398191,0.01150853,0.00000698632,0.7622879,0.0002289489,0.2242052],"study_design_scores_gemma":[0.00003476859,0.00002629536,0.00006474818,0.0004478782,0.00001716191,0.000004640527,0.0006031816,0.5134348,0.00008346498,0.4310943,0.05375764,0.0004310989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005180968,0.004399164,0.8752367,0.002784092,0.0004788584,0.001058824,0.00001463232,0.0002878356,0.1152218],"genre_scores_gemma":[0.7074255,0.00393374,0.1438033,0.0004404471,0.000464902,0.001357007,0.0004369899,0.0001988297,0.1419393],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7314334,"threshold_uncertainty_score":0.9998999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0347162747366038,"score_gpt":0.273585018793439,"score_spread":0.2388687440568353,"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."}}