{"id":"W4223434371","doi":"10.1109/tpami.2022.3166894","title":"Graph Learning on Millions of Data in Seconds: Label Propagation Acceleration on Graph Using Data Distribution","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"National Key Research and Development Program of China; Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Margin (machine learning); Graph; Labeled data; Range (aeronautics); Task (project management); Raw data; Key (lock); Data modeling; Pattern recognition (psychology)","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":[0.0005413618,0.000202191,0.0002802078,0.0007972503,0.0004567339,0.00007482609,0.001160489,0.00004356853,0.00004314014],"category_scores_gemma":[0.00001127805,0.0001980429,0.0000795456,0.003089606,0.00005482435,0.0007699367,0.00006455962,0.000638713,0.000001430214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005799029,"about_ca_system_score_gemma":0.00002245948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000591249,"about_ca_topic_score_gemma":0.001269012,"domain_scores_codex":[0.9976771,0.0002958164,0.0004949571,0.0008830734,0.0004317091,0.0002173508],"domain_scores_gemma":[0.9981088,0.0002012243,0.0002517002,0.001326906,0.00005050321,0.00006087789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000299405,0.0002858214,0.0006765847,0.000009010297,0.0001029011,0.000005031986,0.00009897039,0.6795476,0.0005593906,0.0001461086,0.000004496932,0.3185342],"study_design_scores_gemma":[0.0001442126,0.0002684261,0.000825963,0.0000294669,0.0001335963,0.000005294169,0.00006055305,0.9889178,0.009010401,0.0003798654,0.00002553117,0.0001988423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0409971,0.00006188872,0.9577491,0.0001894511,0.000136457,0.0001993925,0.0006173676,0.00004347929,0.000005735216],"genre_scores_gemma":[0.9975513,0.000217632,0.001292845,0.0001445024,0.00001054613,0.00001854745,0.0007423013,0.00001051073,0.00001179036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9565542,"threshold_uncertainty_score":0.8075954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0763549678641931,"score_gpt":0.322029161367434,"score_spread":0.2456741935032409,"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."}}