{"id":"W4226159313","doi":"10.1109/tifs.2022.3198283","title":"Towards Private Learning on Decentralized Graphs With Local Differential Privacy","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Hong Kong Polytechnic University; Research Grants Council, University Grants Committee","keywords":"Differential privacy; Computer science; Theoretical computer science; Social graph; Graph; Information privacy; Artificial intelligence; Machine learning; Computer security; Data mining; Social media; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.0001929253,0.0001937696,0.0001753151,0.000276357,0.000803387,0.0002201238,0.002761171,0.00007132042,0.00004509569],"category_scores_gemma":[0.00007820287,0.0001728747,0.00006251417,0.0005097052,0.0001375281,0.001196463,0.0005558924,0.0007740987,0.0000079394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001098378,"about_ca_system_score_gemma":0.00005241387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003527739,"about_ca_topic_score_gemma":0.000005617251,"domain_scores_codex":[0.9985186,0.00007427709,0.0002942582,0.000249654,0.0005651663,0.0002980102],"domain_scores_gemma":[0.9981956,0.00005813361,0.0001481147,0.001449676,0.00006272622,0.00008576996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000798867,0.0004436164,0.0001842096,0.0001288056,0.0002387393,0.00001922035,0.006317113,0.03005794,0.00005517381,0.1756891,0.007297868,0.7787694],"study_design_scores_gemma":[0.002675436,0.00147553,0.0004213494,0.00004288203,0.00003398488,0.00009599519,0.0004326032,0.7865283,0.007046019,0.1788281,0.02177742,0.0006423443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1281791,0.000005508833,0.8685188,0.001997053,0.0003563083,0.000230004,0.00005892566,0.0004608048,0.0001935031],"genre_scores_gemma":[0.9860465,0.00007246281,0.01351871,0.0002549379,0.000003874203,0.00005806937,0.0000337791,0.000007898521,0.000003792784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8578673,"threshold_uncertainty_score":0.7049626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01142769745788969,"score_gpt":0.2249037720772502,"score_spread":0.2134760746193605,"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."}}